Category Archives: Divers

Speech recognition for newly documented languages: highly encouraging tests using automatically generated phonemic transcription of Yongning Na audio recordings

Automatic speech recognition tools have strong potential for facilitating language documentation. This blog note reports on highly encouraging tests using automatic transcription in the documentation of Yongning Na, a Sino-Tibetan language of Southwest China. After twenty months of fieldwork (spread over twelve years, from 2006 to 2017), 14 hours of speech had been recorded, of which 5.5 hours were transcribed (200 minutes of narratives and 130 minutes of morphotonology elicitation sessions). Oliver Adams, the author of mam, an open-source software tool for developing multilingual acoustic models, volunteered to experiment with these data. He trained a single-speaker automatic speech transcription tool over the transcribed materials and applied it to untranscribed audio files. The error rate is low: on the order of 11% of errors in phoneme identification. This makes the automatic transcriptions useful as a canvas for the linguist, who corrects mistakes and produces the translation in collaboration with language consultants.

Today I am posting my initial report to Oliver Adams, written in the field in Yunnan, on May 12th, 2017. I consider this date as a landmark in my work documenting Yongning Na! This document remained confidential until today because its online availability would have de-anonymized a submission by Oliver Adams & collaborators that was under double-blind review for a conference in Australia. (This paper, which presents Oliver’s work to an audience of language technology specialists, is now accepted, and will be finalized in the next few days; in the meantime, the submitted version is available here.)

Initial report to Oliver Adams
about the usefulness of the automatically generated phonemic transcription of Yongning Na audio recordings by speaker F4 (Mrs. lɑ˧tʰɑ˧mi˥ ʈæ˧ʂɯ˧lɑ˩mv̩˩)

Summary

I am delighted that you took the time to develop a statistical model for this particular speaker of this particular language. I was initially skeptical about the usefulness of having a first-pass automatic transcription to improve manually. My expectation was that having to correct mistakes generated by the algorithm would add to the workload (wading through an imperfect transcription), and that this would not be faster than the old method (inputting from zero, without an automatically generated transcription to start with), and less straightforward. But as soon as I began using the transcription, I found it pleasant and useful. I am keen to continue the exchange and participate in plans such as the deployment of this tool for all the languages in the Pangloss Collection.

Detailed report

After receiving your sending on May 3rd, a quick preliminary operation was performed : removing all spaces (automatically), so as not to have to remove spaces manually inside each syllable, thus : l ɑ ˩ to lɑ˩. Then I set out to use it as a basis to produce a full annotation of the classical type: transcription plus translation and comments.

  1. My experience of listening to sentences and adjusting the transcription

When revising the automatically generated transcription, I add tone group breaks (the  |  signs), punctuation, and nonlinguistic gap-fillers: əəə... and mmm... (oral filled pauses and nasal filled pauses). I adjust (correct) the transcription and add comments (lines starting with %) and a sentence-level translation in French. (I add Chinese later on, and English even later.)

I tried two methods : (i) improving the transcription on my own, listening to the recording, and making a note of passages where there is something that I do not understand or am not fully sure about, and which I need to ask the consultant later; (ii) working with the consultant, advancing through the automatically generated transcription together with the consultant, and asking her questions as they arise. Both methods work. The former is good for situations where the consultant’s availability is limited: in a short work session, the work focuses on the points that require the consultant’s expertise. The latter is safer and more luxurious for the linguist: as I listen to the audio and amend the transcription, I read aloud each sentence of the corrected transcription to the consultant, and she can verify if it’s OK, which is always good. Listening sentence after sentence is also more pleasant for the consultant (and, again, safer) because the context is fully clear thanks to the linear progression through the audio; by contrast, ‘jumping’ from one spot to another for verification requires the consultant to remember the context, which is feasible but requires more effort than linear progression through a document.

Using the automatically generated transcription, I completed transcription of the HOUSEBUILDING2 narrative, a document of 29’59’’. Transcription of this recording had been slow, extending over several field trips whose main focus was on other topics (study of tone, and creation of a dictionary): I had transcribed 2 minutes in August 2014, 1’20 in June 2015, and 17’ in May 2016. The last 8 minutes were transcribed in May 2017 (completion : May 9th 2017).

I also transcribed 3’30’’ of BENEVOLENCE. So on this field trip, it’s a total of 9’30’’ using your transcriptions, plus 3’30’’ done before your transcriptions came in. That’s 13 minutes of verified transcriptions, in about 12 hours of work sessions devoted to transcription. Seen from this point of view, the difference with earlier methods is not huge. But it is hard (in fact: impossible) for me to quantify the acceleration gained by using the automatic transcription: as the years go by I am more and more familiar with the language, and the consultant is ever better at explaining, and repeating to confirm the exact pronunciation. This makes it hard to compare transcription speed. Also, about half of transcription sessions is spent discussing with the consultant about all sorts of topics, adding new example sentences to the dictionary, and writing comments of all sorts (the lines that start with % in the transcription document, later converted to a XML <NOTE> tag). What matters is the high quality of the data, and I find that the quality of the HOUSEBUILDING2 transcription is high. So I am, by now, a fully convinced user.

  1. Comments on recognition rate and on errors

The recognition rate is (in my impression) spectacular. Technical successes include the treatment of overlong vowels: phonologically (=for phonemic transcription purposes), lengthening needs to be overlooked, and the software overlooks it. The 500 ms long ɤ in /dʑɤ/ (S1 of BENEVOLENCE) is well recognized, for instance.

Occasional cases where the output is not phonologically well-formed (a syllable without a tone, for instance, or sequences such as kgv̩ in S15 of BENEVOLENCE) are easy for the linguist to spot in the transcription. This did not prove any trouble.

Some phonetic and phonological facts excuse several of the algorithm’s « mistakes » :

  • differences between u in your notation and o in mine (or the other way round) should not count as errors, as there are almost no contrasts in Yongning Na (and hence instances of /u/ are few). Phonetically, the transcription of [o] and [u] sounds by your system is good. A higher-level filter operating on syllables could adjust to ‘my’ phonemic analysis with 100% confidence: all instances of /jo/ and /ju/ and /ʝo/ and /ʝu/ in ‘your’ output can be translated to /jo/ in ‘my’ system, as the other combinations don’t exist (under ‘my’ phonemic analysis). Differences between M and H tones in initial and final position inside tone groups should not count as mis-categorizations, either, since the contrasts between H and M are neutralized in tone-group-initial position, and neutralized in tone-group-final position following a L tone. (Sorry if this sounds awfully complex; in fact, this neutralization rule is not so hard.)
  • There are a few loanwords in this text, such as « Taiwan » and « Japan », borrowed through Southwestern Mandarin. Loanwords contain a few otherwise unattested combinations : « Japan », /ʐɯ˩pe˧/, has a /pe/ syllable otherwise unattested in Yongning Na, which only has /pi/, realized as [pe]~[pi]. The automatic transcription, / pi /, is acoustically fine.
  • ʐ instead of ʈʂʰ, in S9 : this is a phonetically unsurprising confusion. In the training corpus, /ʈʂʰ/ appears all over the place in the demonstrative (also serving as 3rd person pronoun), a morpheme in which it is strongly hypoarticulated, losing both aspiration and affrication. This is an artefact of the training corpus.

To sum up, errors are few, and they make linguistic sense : they are not (as I feared) random added noise for the transcriber.

3. Benefits for the linguist

  • A benefit which I had not expected is that correcting the transcription allows me to be more alert : in a sense, I am in « proofreading mode », instead of when I type the transcription from scratch. In earlier transcriptions (« pre-mam days »), I made errors due to mis-typing : for instance, I clearly heard a L.L.H.L tone sequence, but somehow typed it as L.L.L.L. Mis-typing is pretty frequent. I keep track of all corrections to texts over the years, so I know about those mistakes. They can be really hard to correct: during fieldwork I make efforts to produce the most accurate possible transcription, in consultation with the language consultant, so I don’t want to change transcriptions later just on the basis of auditory impression, and I must trust the transcriptions. So one mis-typed symbol becomes a problem, if the issue is not spotted at once. If I never realize that something is wrong, it can create trouble later for other people using the data (worst scenario). If I realize later that something sounds wrong, I make a note, and ask the consultant on the next field trip : that takes up some of the (scarce) time of the field trips, and pretty soon (in a few years’ time ?) the consultant won’t be available anymore, at which point I shall simply cease to make corrections for want of being able to double-check with her. So precision of transcription is essential in « my » workflow. Errors can creep in anywhere, anytime, but I feel that the process of seeing the transcription in front of my eyes and correcting it allows me to correct the mistakes more systematically: in a sense, the task is already a « proofreading » one, so (I think) my attention is sharper and the result is better.
  • A benefit that belongs in the same category as those noted in the 2014 paper: having my attention drawn to phonetic facts that I have learnt to overlook because they are not phonemically contrastive. ‘Weak’ words (grammatical morphemes) undergo influence from their environment and get hypo-articulated. For instance, the negation gets transcribed as mõ˧ in HOUSEBUILDING2 (23m50s) instead of mɤ˧. This is interesting for me: now that I think of it, the vowel in that syllable is probably nasalized, and acoustically unlike the average ɤ vowel of ‘full’ words (lexical words). This is the stuff that phonetic evolutions are made of, explaining why and how grammatical morphemes follow phonetic evolutionary paths that are different from the rest of the lexicon.
  • The automatically generated transcription removes the risk of overlooking a repetition of a word. In casual oral speech, there are repetitions, hesitations etc, which hearers normally process in a ‘nonlinear’ way, factoring out dysfluencies etc. As I am committed to transcribing everything on the recording (not producing a ‘groomed’ text with the audio as a mere prompt to the consultant), I need to make efforts to ‘linearize’ the recording in the transcription: for instance, if a word is repeated five times, in “pre-Oliver Adams times” I used to pause, count the repetitions on my fingers, and carefully input all of those. This requires attention, and sounds a little ridiculous to the consultant, as she feels (rightly, I must say!) that this hyperbolic emphasis on form detracts from the “core” linguistic work in which she participates: explaining the meaning to me, explaining difficult words, etc. Now, with the automatically generated transcription, repetitions are all “linearized” in the first place, and I need to devote less attention to producing the transcription. Less attention devoted to typing letters and checking that I have not forgotten a word (or a longer passage) makes me more confident about the progression along the narrative, and hence more ‘available’ for the consultant for meaningful discussions about this and that. I less frequently need to tell the consultant “Wait for me a minute” while I go forward / backward in my notes. A couple of times I lost track of where I was in the automatically generated transcription, but thanks to the indication of time provided inside the automatically generated transcription it was not hard to get back on track.
  1. Ideas for future refinement
  • Add an indication where the algorithm is ‘skating on thin ice’ for recognition : such as when several candidates are about equally likely. This could for instance be added as a tag inside the transcription, and, in turn, be displayed with a special colour in an editor (an editing interface for the linguist). So when the linguist/transcriber looks at a full screen of automatically generated transcription, the passages that are unproblematic would be in green, and those where « confidence » is lowest would be in orange. This is not indispensible, of course : fussy people like myself want to produce « haute couture » pieces (linguistic annotation as a fine art !), and so they’ll want to check every word no matter how obvious it is that the automatic translation is already fine. On the other hand, if « your » tool is intended for rapid transcription of large volumes of data, it would be great to direct the user’s attention to places where verification seems particularly necessary.
  • A big piece of work : improving tone recognition. How is tone recognition conducted now : is it independently computed for each syllable ? In view of the importance of syntagmatic effects on tone in Na (=effect of the position of the tone inside the sequence of tones, and relative to the boundaries of tone groups), the model could be improved based on a « window model » relying on linguistic hypotheses on (i) possible sequences of phonological tones and (ii) expected phonetic implementation for these tone sequences. This would suppose arriving at a division into breath groups and smaller units (roughly corresponding to « sentences » and, inside sentences, to tone groups). If someone is interested to work with me on this, there are explanations and hypotheses in Chapter 8 of the book ; I think of these as a basis for future experimental phonetic studies, and dialogue with speech recognition would be super. Currently, tone recognition is not bad at all, but there is a lot of room for improvement. Given the nature of the tone system, I think that approaching 100% would be much, much easier than in languages such as Mandarin and many (most ?) other Chinese dialects.
  • A phonetician’s question : Is there any way to look under the hood and see which acoustic properties are used to identify the various phonemes? That is, the (relatively) stable properties that allow for the successful identification of a given consonant or vowel. I understand that the statistical models are not based on properties that can be straightforwardly identified with acoustic cues ; and I guess that if retrieving acoustic ‘features’ from recognition models were easy to do, it would have been done a long time ago (for the languages for which good recognition systems exist). But your achievements raise my expectations about what is possible !

In the coming months (after your PhD defense), I hope you will be willing to continue the dialogue and continue improving the system. If there were a way for me to ‘feed’ new transcriptions into the system to improve it, or to ‘re-train’ it anew with improved versions of the transcriptions, that would be terrific. The system is currently good enough to be useful ; I (for one) am interested to improve it further, to the point where Yongning Na has a good recognition system for that one speaker, and perhaps even a translation module – now is a time to dream ! 🙂

  1. Beyond consultant F4 and myself : Expectations of the Pangloss Collection ‘community’

Receiving the high-quality automatic transcriptions was extremely exciting for me. I talked about this to Guillaume Jacques & his students Lai Yunfan and Gong Xun. They are revolutionizing Sino-Tibetan studies by their work on Rgyalrongic languages (a group of dialects/languages that are as important to Sino-Tibetan as Sanskrit to Indo-European). Guillaume’s one-line answer was « C’est vraiment génial, si ce monsieur a du temps à consacrer au japhug, je lui saute dessus. » :: “This is great. If this gentleman has some time to devote to Japhug, I shall pounce on him.” You may remember my mentioning Japhug Rgyalrong in our earlier correspondence : it’s the language on which Guillaume does the most work. He transcribes reams of recordings by himself: he is so advanced that occasional verifications with his consultant are enough. Your tool could greatly accelerate his work. You could build on the availability of a much larger amount of transcribed audio than for Yongning Na. Guillaume does some transcriptions every day. Given his role as a leader in the field, and the importance of the language, the availability of a tool akin to the one you did for Na could do wonders. The Japhug corpus could also be a fantastic ‘playground’ for work on automatic translation. (For tasks beyond phonemic transcription: Guillaume wrote a dictionary of 7,000 entries.)

Of course everything takes time; doing a Japhug recognition tool would require understanding how he works and a couple of special conventions he uses. He is less finicky than me concerning phonetic detail, so I think he sometimes just leaves aside repetitions, hesitations and dysfluencies (whereas I try to transcribe everything), so perhaps that could make the training procedure slightly harder (due to occasional mismatch between transcribed string and audio signal).

Other colleagues, such as Alex François, also have large data sets that could be appropriate (dictionary+abundant texts). Guillaume and Alex are both interested to invest the time to make the most of brilliant technology like the one you developed for Na.

Let me stop here for now ; you can sense that I don’t feel as if this were the end of the story. Félicitations !

Yunnan, May 12th, 2017

 

Alexis Michaud

I'm a linguist specialized in phonetics, focusing on un(der-)documented languages.

More Posts - Website

Follow Me:
LinkedIn

“Tone in Yongning Na” now published!

Book cover: Tone in Yongning Na

The volume Tone in Yongning Na is now published.

It is open-access: the books is freely available as a PDF from the publisher’s website.

It is open-source: the LaTeX code is freely available on GitHub (from the same page as the PDF).

Last but not least, the analyses are based on data hosted in an open archive (the Pangloss Collection) that allows free download of original sound files and transcriptions (no login required).

I think I should now let the book speak for itself 🙂 and thank once again the many colleagues who helped all along the way.

One of the aims of this blog post is to spread the word about the publishing house. Publishing a book at Language Science Press was a sparkling experience all along. If you do not know about Language Science Press yet, I strongly encourage you to read the description of the “Motivation”, “Setup” and “Vision” of this wonderfully forward-looking publisher. And if you like the project, you can help with the ongoing fundraising drive of Language Science Press (described here) by talking to your librarian about financial support to the publisher. (Feel free to get in touch with me if you would like to discuss this topic.)

Alexis Michaud

I'm a linguist specialized in phonetics, focusing on un(der-)documented languages.

More Posts - Website

Follow Me:
LinkedIn

Project completed! Looking back at the past 48 months, and forward to online grammars and more connected data

The project completion date is December 31st, 2016. This is the time to look back at the past 48 months, and forward to more and more connected data: online grammars with one-click links to data, and other improvements for the greater benefit of linguistic research.

The aim of this project was to build several types of corpora (traditional stories and dictionaries) for unwritten and endangered Sino-Tibetan languages spoken in Nepal and in Tibetan areas of China (Khaling, Thulung, Koyi, Japhug, Zbu, Khroskyabs, Na), as well as to produce tools to analyze and format these corpora. We were able to develop a dictionary interface on the Pangloss collection website (http://lacito.vjf.cnrs.fr/pangloss/dictionaries/), and an online tool of parallel corpus comparison (http://himalco.huma-num.fr/corpus/comparable/index.htm and  http://lacito.vjf.cnrs.fr/pangloss/dictionaries/). The Khaling, Thulung, Japhug and Na corpora of the Pangloss collection were also significantly enriched.

The software engineer Céline Buret collaborated with us during 24 months. She developed a python library called pylmflib (https://pypi.python.org/pypi/pylmflib/1.0) which implements in XML the lexicographical norm LMF, with conversion tools from the MDF format (used by many fieldwork linguists to make their dictionaries) to LaTeX, HTML and DOC. PDF versions of the dictionaries (available on the website http://himalco.huma-num.fr/dictionaries/index.htm and on HAL-SHS) have been generated using LaTeX, and a paper version of the Khaling dictionary has been derived from it.

In the wake of the HimalCo project, new tools are being developed for the pylmflib library (conversion of the LMF dictionaries to Android format, graphical interface) to allow the production of multimedia dictionaries in other languages studied by linguists from CNRS and other institutions, in France and abroad.

For the Khaling dictionary, a set of PERL scripts have been written to (i) automatically generate the conjugation paradigms (ii) automatically convert from API to Devanagari script.

To sum up, this project has made possible to realize three types of corpora :

  • Three dictionaries of unwritten and endangered languages: Khaling, Na and Japhug. In the case of Japhug and Na, these dictionaries are the first to be available for these languages. As for Khaling, it is the first dictionary in a reliable transcription, which provides in addition the complete conjugation paradigms, of crucial importance in this language.
  • A corpus of 64 hours of audio recordings (and in part video) transcribed and annoted in four languages (Japhug, Na, Khaling, Thulung) has been archived in the Pangloss collection, which is thus significally enriched by 555 new documents.
  • A pilot interface of parallel corpus comparator, using some of the traditional stories from the corpora of Kiranti languages.

Scientific publications based on these data can be looked up here (full-text, no login required).

We now look forward to further experiments and realizations in the publication and exploitation of the results of linguistic analysis.  The idea is to put together a complete set of linked electronic resources comprising grammars, dictionaries, text corpora, and multimedia documents. This work gradually consolidates the empirical basis of the formulations and models proposed in typology and language theory. We hope you will want to continue to follow us, now on other blogs and websites (see in particular Panchronica — in French — and of course the Pangloss Collection).

Alexis Michaud

I'm a linguist specialized in phonetics, focusing on un(der-)documented languages.

More Posts - Website

Follow Me:
LinkedIn

“Tone in Yongning Na” is the first book to enter Open Review stage at Language Science Press!

The HimalCo project allowed for the completion of the linguist’s “three treasures” for the Yongning Na language: a dictionary; a collection of texts; and a monograph. This monograph was submitted in June 2016 to Language Science Press.

Language Science Press publishes high quality, peer-reviewed open-access books in linguistics. All publications are free for both authors and readers. General Editors are Stefan Müller (FU Berlin) and Martin Haspelmath (MPI for the Science of Human History). They are supported by a high-profile Advisory Board.

The book, entitled “Tone in Yongning Na: Lexical tones and morphotonology”, was accepted in October 2016. Anonymous reviewers provided a wealth of comments and suggestions, which were gratefully implemented. Now “Tone in Yongning Na” is the first book to enter Open Review stage at Language Science Press. I hope you will want to have a look!

Two quick notes for readers:
(i) The draft that is currently open for you to review has a few unsightly page breaks and line breaks: for instance, the word “construction” begins at the end of page 144 (“construc-“) and the ending (“tion”) is orphaned on page 147. Some examples are also split over two pages. And a few lines spill into the margins. Please kindly disregard these issues concerning page breaks and line breaks: we’re aware of those, but page breaks and line breaks will only be finalized at the very end of the typesetting stage.
(ii) It seems that the PDF made available on the reviewing interface, PaperHive, is not searchable. It makes it hard to navigate the volume. In case you struggle with this, you can download the (searchable) PDF at the following address:
https://www.dropbox.com/s/nekau4g6q91tg6t/109ToneInYongningNa_Draft_21Dec.pdf?dl=0
You can then EITHER provide your comments by logging in to PaperHive and locating the places you have comments about, OR send me comments by e-mail (alexis.michaud@cnrs.fr). All comments will be gratefully acknowledged whether transmitted through PaperHive or by e-mail.

Alexis Michaud

I'm a linguist specialized in phonetics, focusing on un(der-)documented languages.

More Posts - Website

Follow Me:
LinkedIn

Nepal News

wnp1218hf_-00_nepal-flag-12-x-18-inch

Like anyone with a strong attachment to Nepal–and many more besides–we were heartbroken to witness from afar the two major earthquakes which devastated Nepal on April 25th and May 12th. Thankfully, the individuals we work with most closely have all reported that they are safe. While there was serious damage in Solu district, where the Rai languages are spoken, it seems that the number of casualties was not as high as was initially feared.
The French government is for the time being not allowing French civil servants (a status covering French academics) to travel to Nepal. As a result, we are working to bring a Thulung speaker to Paris during the summer, which will allow us to continue to work on these amazing languages while giving Nepal time to recover from its wounds.  We still hope to return to Nepal in the fall–Nepal has expressed that the best way to help is to travel to the country, as it relies so much on tourism–and will find ways to spread the word about these languages either way.

Project currently developing on GitHub — out of public view

The project blog has gone quiet in the past 5 months, as texts and dictionaries are in the making in a (nonpublic) GitHub repository. Tools for data migration from Toolbox / MDF format to XML and LaTEX are now operational. Painstakingly collected linguistic data and innovative technology make a heady cocktail: we were excited to see the very earliest professional-looking draft versions of our dictionaries.

Aimée Lahaussois made a field trip to Nepal earlier this year; Guillaume Jacques is beginning one in Southwest China; and this post’s author will visit again Yongning (also in Southwest China) in August. Lots of tasks are under way. In GitHub jargon: hundreds of ‘Commits’ (updates of documents and scripts), 9 Wiki pages, (currently) 33 ‘Issues’ (tasks to be done)… and high hopes of having great things to showcase here in due course.

Alexis Michaud

I'm a linguist specialized in phonetics, focusing on un(der-)documented languages.

More Posts - Website

Follow Me:
LinkedIn

Third Workshop on Sino-Tibetan Languages of Sichuan: a brief report

Last month our team organised the third edition of the Workshop on Sino-Tibetan Languages of Sichuan, which followed a first workshop in Taipei organised by Jackson T.-S. Sun, and a second one in Beijing in 2010. The conference was hosted at the EHESS.

Alexis Michaud set up a lively website for the workshop. A Book of abstracts is available.

Nearly all fields of linguistics were represented during this conference, and the proportion of papers on phonology and phonetics vs. morphosyntax was relatively well balanced.

It may be unappropriate for me, as one of the co-organizers, to praise the success of our workshop. Yet, I think that it was noteworthy in at least one respect. The advantage of small-scale workshops like this one is that people working on closely related research topics can get together and interact with each other in a better way than in huge conferences. In this workshop, we established a record for the number of presentations on Naish (four) and Rgyalrongic (eight). The presentations on these languages also happened, for some of them at least, to be on related topics: all papers on Naish were about tonology, in particular. This allowed detailed and productive discussions both during the question sessions and during breaks, and it was quite a rewarding experience — at least for me.

Among the participants at the conference were three native speakers of the languages under investigation: Wang Shuangcheng (speaker of Amdo Tibetan and dialectologist himself), Skalbzang Phuntshogs (whose name is sinicized as Geiru Pincuo, a speaker of Northern Pumi collaborating with Henriette Daudey on language documentation) and bLobzang Nyima (a speaker of Rtau [rəsɲəske] who lives in Paris and collaborates with our team). Their presence was in my opinion an essential element of the success of this workshop: during discussions, it allowed for immediate reverification of data cited by participants. It is already a tradition, since 2008, for the Sichuan Workshop to include native speaker participants, and I hope that this tradition will continue in further instalments of this conference.

Zev Handel has expressed his interest to organize the next workshop in Seattle, and I look forward to it already.

Victor Segalen: an explorer who gave a bad name to foreign scholars in China

A Chinese friend doing archaeological work once asked me, ‘Have you heard about Victor Segalen?’ (謝閣蘭) And then, ‘What do you think about him?’

Before our discussion, my impression was positive. I liked Segalen’s literary works; and I believed that Segalen was equally serious about exploring China. Unlike others, he learnt some Chinese; and he went to faraway places, (re-)discovering major archaeological sites. His style of writing is decidedly on the romantic, passionate side, lacking the kind of matter-of-fact information that is required for serious scholarship, but poetic licence seemed OK on the part of an explorer from the last years of Imperial China. There are some obnoxious colonial overtones in some of his writings, but that too seemed OK if viewed in the context of his time.

My Chinese friend’s perception was different. As an archaeologist, he pointed out that Segalen had unearthed sculptures, taken pictures, and gone his own sweet way, leaving ancient art objects exposed to the elements and to depredation, without even reporting their location in sufficient detail. That was an eye-opener for me. Inspired literary works cannot serve as an excuse for leaving a mess behind. As an archaeologist, Victor Segalen simply did not do a serious job. When in a foreign country, one is seen, willy-nilly, as a representative of one’s own country; and so Segalen gave a bad name to foreign scholars in China.

The morality for linguists is simple. When we go and collect data, beyond our immediate interests it’s important to think in terms of stable repositories that guarantee long-term conservation and online availability for researchers and for the communities.

Alexis Michaud

I'm a linguist specialized in phonetics, focusing on un(der-)documented languages.

More Posts - Website

Follow Me:
LinkedIn

Incentives for publishing text corpora and multimedia documents: About a recent discussion on the Tibeto-Burman list

In-depth language documentation is clearly a priority duty for linguists of our generation. This is what will remain as our most important legacy. It is also a major driving force for real advances in linguistics, as multimedia digital databases open up a tremendous potential for testing linguistic analyses and building computer models: a huge space opens up once we have a reliable, high-quality empirical basis for our studies.

This point has been made eloquently in various forums; it can now be considered a rather uncontroversial point of view. Realizations tend to lag behind somewhat, though. In addition to personal conviction, institutional recognition is required for academics to invest as much time as they should (and in many cases would like to) into the time-consuming tasks of preparing data for long-term preservation, online circulation, and further computer processing. There has been a vivid discussion about publications and publication venues on the Internet list “Issues and Announcements Related to Tibeto-Burman Linguistics” lately (Tibeto-Burman internet domain). Stephen Morey pointed out that:

“Here in Australia, the Australian Linguistics Society has set up a subcommittee to work out ways by which text corpora – annotated, analysed and curated – can be assessed and counted as research output just as articles in journals are. This follows on the recognition of the scholarly merit of Language Documentation by the Linguistics Society of America in 2010.
Once academics can get credit for this kind of work, we’ll be able to put more time into it and this will be of benefit to communities in the long run as well.”

This was a response to Guillaume’s suggestion: “I think that our community should value more the production of dictionaries and text collections including translations in the local national languages, not just in English (or even only in the local languages, without English), even if this kind of publication never get cited. Citation-based evaluation of academic productivity has a highly detrimental effect on the field, and evaluators should really make a special case for non-English publications intended for speakers of the endangered languages.”

To me, the exchanges over the Tibeto-Burman list conveyed a keen sense of the excitement of doing linguistics on under-resourced languages. This is an era for pioneers, and the frontier is… in our own gardens, which we must cultivate, following the motto of the Pangloss Collection! The framework is in place: long-term archiving and stable identifiers; open archives for consultation; CreativeCommons licenses… and it’s now a matter of getting one’s act together. In the long run this is well-invested time and effort, as the hours, days and months of manual weeding, pruning and trimming make for great documents, which always find an appreciative audience at some point.

Alexis Michaud

I'm a linguist specialized in phonetics, focusing on un(der-)documented languages.

More Posts - Website

Follow Me:
LinkedIn

Talking dictionaries for Himalayan languages

In addition to parallel corpora, the main objective of this research project (HimalCo) is to create a set of online talking dictionaries, in particular from Japhug Rgyalrong, Khaling, Thulung and Yongning Na. We are still weighing our options concerning the structure of the platform (in particular, whether or not to use LexiquePro), but we have decided that all dictionaries will be encoded in a Toolbox-like format, either directly generated by Toolbox itself or exported from FLEX.

Files in Toolbox format are easily manipulable with PERL scripts. They can be easily converted to HTML and combined with sound files to produce a simple interface for web dictionaries, like the Arapaho talking dictionary (this could be an alternative to LexiquePro):

http://linguistics.berkeley.edu/~arapaho/arapaho_english.html

It is also easily convertible to LaTeX code, which can then compiled into a PDF file to produce a professionally typeset version of the dictionary with hyperlinks for cross-references. We place special focus on online tools, and on the web version of dictionaries, but it is also necessary to have printed versions accessible to the speakers of the languages.

Also, it is trivial to write PERL script to convert from one writing system to another (for instance, from IPA to Devanagari script in the case of languages of Nepal) and to automatically generate entire paradigms for either the complex verbal flexion of the Kiranti languages or the intricate tonal alternations of the Naish languages.

Within the three years time frame of this project, it would be irrealistic to work on lots of dictionaries at the same time. For this reason, we decided, in the case of the three Kiranti languages under study, to compile verb dictionaries only. These dictionaries will comprise all the verb roots, their derived forms, example sentences, and a complete list of automatically generated paradigms. This is also a better service to the communities, as many Rai (Kiranti ) intellectuals attempt at making dictionaries themselves, but experience diffculty with the complex verbal morphology of their languages.

I have finished a first draft of the Khaling verb dictionary (the example sentences were collected during my field trip in Solukhumbu last February), and I am bringing it to Nepal next week for proofreading, finishing the section on complex predicates and recording the examples for the web version. This dictionary will continue to improve over the years; on the other hand, a first publishable version is now in view, and I hope that it can soon be made available to native speakers as a practical, easy-to-use book.

On the notion of parallel corpora

We borrowed this idea from the field of translation studies, where translation equivalents are aligned and then stored as translation memory to be used during later translation tasks.  What interested us was the idea of aligning linguistic data across languages and retrieving aligned segments for the purposes of analysis and comparison.

One of the remarkable features of Kiranti languages in Eastern Nepal is that their mythology is surprisingly similar: in some cases, perfect calques of sentences are found across different language versions of a same story.  This seemed like a good starting point for building a corpus of aligned material based on resolutely native data, as opposed to more artificial (but still interesting) material such as Frog stories and Pear Stories.

We have set up a prototype for the aligntment of stories, and so far, it is quite promising:  we have aligned three different versions of the story of Kakcilip–in Thulung, Koyi and Khaling–in such a way that similar content across languages is tagged with a Similarity label.

The Similarity labels appear above the sentence numbers in the full-text versions of the story in the different languages. When a sentence with such a label is selected, it leads to a view of that same sentence in the languages involved in the similarity.

We had, of course, to define the notion of similarity for the purposes of this alignment: for the time being, our working definition is that it concerns a segment of text of similar narrative function or content.  This allows us to align, in addition to material sharing lexical and morphosyntactic features, sentences in different versions that outwardly have no connection (different names of protagonists, different actions, different objects involved) but that share narrative function, in being, for example, a turning point within the story.

The ability to see the same (or a similar) sentence across languages makes it possible to identify the individual languages’ available tools for expressing similar material.

We have also associated a concordancer with the aligned corpus, which means that we can look for specific morphemes or lexemes and then compare them across languages.

For more details on the technical set-up, you can see our paper presented at LREC 2012, in a workshop on Building and Using Comparable Corpora.

About Exploratory Field Trips

These days, the project team is busy finalizing administrative issues. One slight difficulty is that the funding agency, the Agence Nationale de la Recherche, does not have a separate category for exploratory field trips: trips to the areas where the languages we study are spoken, and where we collect the data which is then organized, made available online (in the Pangloss Collection) and analyzed. In the budget documents, they are pooled together with the budget items for attending conferences, workshops… As a result, linguistics project with a fieldwork component look pretty strange from the point of view of current administrative/accounting standards. It looks as if too much money were spent on international travel.

This administrative episode gives us an opportunity to emphasize the specificity of exploratory field trips, which are central to our work. Fortunately, the people at ANR are open to suggestions and interested in understanding how our work is actually conducted, so the odds are that we shall be able to carry out numerous field trips, as originally planned. Who knows–perhaps exploratory field trips will even come to be recognized as a special category of “mission” in administrative typology? At some research centres with a strong tradition of fieldwork, such as LACITO, the two (“Conferences/Workshops” and “Fieldwork”) are already distinguished, as a matter of course.

 

Alexis Michaud

I'm a linguist specialized in phonetics, focusing on un(der-)documented languages.

More Posts - Website

Follow Me:
LinkedIn

HimalCo – Himalayan Corpora

This project proposes to build parallel corpora for three sub-groups of the Sino-Tibetan family, covering a total of 8 little-described oral languages. These corpora will be made up of texts and lexical data. Texts that share a similar (sometimes nearly identical) narrative frame will be selected, drawing from the strong mythological traditions of the Greater Himalayan region. One set of parallel texts will be assembled for each sub-group: Kiranti (from Nepal), and Rgyalrong and Naish (from China). (Note that “parallel texts” in the sense of our project does not refer to texts with aligned translation, as in “parallel Classical Greek texts”: Greek on one page and English on the facing page, but to traditional texts put in parallel according to the junctures of their narrative frames.) The alignment of texts on the basis of their narrative frame will allow for the cross-language comparison of highly similar native materials; among other benefits for research, the typologically salient features of each sub-group will thus come to the fore with greater accuracy than can be obtained through the type of elicitation often used for cross-language comparison, e.g. the Pear Story.
HimalCo includes the two essential steps of (i) first-hand data collection in the field (in Nepal and China) and (ii) state-of-the-art transcription, annotation and formatting of the entire data set. In addition to classical interlinear morphemic glossing, translation and sound synchronization as implemented in the LACITO Archive (to which the participants are regular contributors), the narratives will be organized into parallel corpora in each of the three language subgroups, and the lexical data will be serve as the basis for talking dictionaries: dictionaries combined with sound recordings of individual entries (words spoken in isolation) and of example sentences.
The team, which includes an IT specialist, will develop simple interfaces for the consultation of parallel corpora and talking dictionaries, allowing the comparison of material in individual languages, across languages of a subgroup, and across subgroups. This project will provide the solid empirical basis which has heretofore been lacking for research on these languages: all the materials will be made freely available online through the LACITO Archive, whose interface will be enriched to allow consultation of parallel texts and talking dictionaries. These objectively verifiable data will be available for the in-depth investigation of a broad range of issues that include topical issues in synchrony and diachrony (comparative morphology; reconstruction of Tibeto-Burman morphology; and study of the evolution of morphological systems) for which these languages have key evidence to contribute.

Alexis Michaud

I'm a linguist specialized in phonetics, focusing on un(der-)documented languages.

More Posts - Website

Follow Me:
LinkedIn