Korea, Republic of

Deep nets are great, and they would be even greater if they could collaborate with each other through a flexible communication protocol. Since many networks come equipped with language model interfaces--that is, they can process and produce tokens in English (or other languages)--it makes sense to look into natural language as a universal neural network communication protocol. The questions I would like to discuss in my talk, then, are the following:&lt;br&gt;
* What are the challenges we face in developing a universal language interface among deep networks?
* What do we currently know about the way in which deep nets are using language to interact in machine-to-machine communication scenarios?
* Which characteristics of human linguistic communication do we expect or wish machine-to-machine communication to possess? Should it be essentially the same as human-to-human (and human-to-machine) communication?

COLING 2022

Machine-to-machine communication: Do we need it? What should it be like? Is it &quot;language&quot;?

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

IJCNLP-AACL 2021

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

Deep nets are great, and they would be even greater if they could collaborate with each other through a flexible communication protocol. Since many networks come equipped with language model interfaces--that is, they can process and produce tokens in English (or other languages)--it makes sense to look into natural language as a universal neural network communication protocol. The questions I would like to discuss in my talk, then, are the following: 
* What are the challenges we face in developing a universal language interface among deep networks?
* What do we currently know about the way in which deep nets are using language to interact in machine-to-machine communication scenarios?
* Which characteristics of human linguistic communication do we expect or wish machine-to-machine communication to possess? Should it be essentially the same as human-to-human (and human-to-machine) communication?

Machine-to-machine communication: Do we need it? What should it be like? Is it "language"?

keynote

[![](https://assets.underline.io/uploads/markdown_image/1/image/81a3c0317d24f663b49b996875024d45.png)](https://aclanthology.org/volumes/2022.coling-1/)



### THE CONFERENCE WE KNOW AND WE WANT.
**COLING**, the International Conference on Computational Linguistics, is one of the premier conferences for the natural language processing and computational linguistics.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes but also in industrial research departments including tech-startups. COLING provides opportunities for all these communities to showcase their exciting discovery.

In fall of 2022, COLING will be held in Gyeongju in a hybrid format. All participants can either present at the venue site or join virtually. As more people get vaccinated, we are happy to provide safer environments for our colleagues. We believe that COLING 2022 will be one of the conferences, free from the pandemic. The hybrid format gives presenters and sponsors a valuable opportunity to promote their companies in both an online and in-person venue. For the first time in a long time, customers can interact with their sponsor's products first-hand. The online venue, too, gives sponsors the chance to network with those unable to attend the in-person session.

The hybrid format ultimately lends itself to greater exposure for our sponsors: COLING2022 will let you reach more potential partners and customers than ever before!

To gain access to this event page you are required to register. Find more information and pay the registration fee on event the organizer’s website **[https://coling2022.org/reg](https://coling2022.org/reg)**

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for the natural language processing and computational linguistics.

Pro-drop is commonly seen in many languages, but its discourse motivations have not been well characterized. Inspired by the topic chain theory in Chinese, this study shows how character-verb usage continuity distinguishes dropped pronouns from overt references to story characters. We model the choice to drop vs. not drop as a function of character-verb continuity. The results show that omitted subjects have higher character history-current verb continuity salience than non-omitted subjects. This is consistent with the idea that discourse coherence with a particular topic, such as a story character, indeed facilitates the omission of pronouns in languages and contexts where they are optional.

Quantifying Discourse Support for Omitted Pronouns

Humans process natural language online, whether reading a document or participating in multiparty dialogue. Recent advances in neural coreference resolution have focused on offline approaches that assume the full communication history as input. This is neither realistic nor sufficient if we wish to support dialogue understanding in real-time. We benchmark two existing, offline, models and highlight their shortcomings in the online setting. We then modify these models to perform online inference and introduce rollback: a short-term mechanism to correct mistakes. We demonstrate across five English datasets the effectiveness of this approach against an offline and a naive online model in terms of latency, final document-level coreference F1, and average running F1.

Online Coreference Resolution with Rollback

Product reviews may have complex discourse including coreference and bridging relations to a main product, competing products, and interacting products. Current approaches to aspect based sentiment analysis (ABSA) and opinion summarization largely ignore this complexity. On the other hand, existing systems for coreference and bridging were trained in a different domain. We collect mention type annotations relevant to coreference and bridging for 498 product reviews. Using these annotations, we show that a state-of-the-art factuality score fails to catch coreference errors in product reviews, and that a state-of-the-art coreference system trained on OntoNotes does not perform nearly as well on product mentions. As our dataset grows, we expect it to help ABSA and opinion summarization systems to avoid entity reference errors.

Analyzing Coreference and Bridging in Product Reviews

We describe a novel approach to transcribing morphologically complex, local, oral languages. The approach connects with local motivations for participating in language work which center on language learning, accessing the content of audio collections, and applying this knowledge in language revitalization and maintenance. We develop a constraint-based approach to interactive word completion, expressed using Optimality Theoretic constraints, implemented in a finite state transducer, and applied to an Indigenous language. We show that this approach suggests correct full word predictions on 57.9% of the test utterances, and correct partial word predictions on 67.5% of the test utterances. In total, 87% of the test utterances receive full or partial word suggestions which serve to guide the interactive transcription process.

A Finite State Aproach to Interactive Transcription

The study of language variation examines how language varies between and within different groups of speakers, shedding light on how we use language to construct identities and how social contexts affect language use. A common method is to identify instances of a certain linguistic feature - say, the zero copula construction - in a corpus, and analyze the feature’s distribution across speakers, topics, and other variables, to either gain a qualitative understanding of the feature’s function or systematically measure variation. In this paper, we explore the challenging task of automatic morphosyntactic feature detection in low-resource English varieties. We present a human-in-the-loop approach to generate and filter effective contrast sets via corpus-guided edits. We show that our approach improves feature detection for both Indian English and African American English, demonstrate how it can assist linguistic research, and release our fine-tuned models for use by other researchers.

Corpus-Guided Contrast Sets for Morphosyntactic Feature Detection in Low-Resource English Varieties

Language documentation encompasses translation, typically into the dominant high-resource language in the region where the target language is spoken. To make data accessible to a broader audience, additional translation into other high-resource languages might be needed. Working within a project documenting Kotiria, we explore the extent to which state-of-the-art machine translation (MT) systems can support this second translation – in our case from Portuguese to English. This translation task is challenging for multiple reasons: (1) the data is out-of-domain with respect to the MT system’s training data, (2) much of the data is conversational, (3) existing translations include non-standard and uncommon expressions, often reflecting properties of the documented language, and (4) the data includes borrowings from other regional languages. Despite these challenges, existing MT systems perform at a usable level, though there is still room for improvement. We then conduct a qualitative analysis and suggest ways to improve MT between high-resource languages in a language documentation setting.

Machine Translation Between High-resource Languages in a Language Documentation Setting

We present the first neural machine translation system for translation between the endangered Erzya language and Russian and the dataset collected by us to train and evaluate it. The BLEU scores are 17 and 19 for translation to Erzya and Russian respectively, and more than half of the translations are rated as acceptable by native speakers. We also adapt our model to translate between Erzya and 10 other languages, but without additional parallel data, the quality on these directions remains low. We release the translation models along with the collected text corpus, a new language identification model, and a multilingual sentence encoder adapted for the Erzya language. These resources will be available at https://github.com/slone-nlp/myv-nmt.

The first neural machine translation system for the Erzya language

This paper describes a procedure to link a Toolbox dictionary of a low-resource language to correct synsets, generating a new wordnet. We introduce a bootstrapping technique utilising the information in the gloss fields (English, national, and regional) to generate sense candidates using a naive algorithm based on multilingual sense intersection. We show that this technique is quite effective when glosses are available in more than one language. Our technique complements the previous work by Rosman et al. (2014) which linked the SIL Semantic Domains to wordnet senses. Through this work we have created a small, fully hand-checked wordnet for Abui, containing over 1,400 concepts and 3,600 senses.

Abui Wordnet: Using a Toolbox Dictionary to develop a wordnet for a low-resource language

In this paper, we present a straightforward technique for constructing interpretable word embeddings from morphologically analyzed examples (such as interlinear glosses) for all of the world’s languages. Currently, fewer than 300-400 languages out of approximately 7000 have have more than a trivial amount of digitized texts; of those, between 100-200 languages (most in the Indo-European language family) have enough text data for BERT embeddings of reasonable quality to be trained. The word embeddings in this paper are explicitly designed to be both linguistically interpretable and fully capable of handling the broad variety found in the world’s diverse set of 7000 languages, regardless of corpus size or morphological characteristics. We demonstrate the applicability of our representation through examples drawn from a typologically diverse set of languages whose morphology includes prefixes, suffixes, infixes, circumfixes, templatic morphemes, derivational morphemes, inflectional morphemes, and reduplication.

How to encode arbitrarily complex morphology in word embeddings, no corpus needed

This paper presents a set of experiments in the area of morphological modelling and prediction. We test whether morphological segmentation can compete against statistical segmentation in the tasks of language modelling and predictive text entry for two under-resourced and indigenous languages, K’iche’ and Chukchi. We use different segmentation methods — both statistical and morphological — to make datasets that are used to train models of different types: single-way segmented, which are trained using data from one segmenter; two-way segmented, which are trained using concatenated data from two segmenters; and finetuned, which are trained on two datasets from different segmenters. We compute word and character level perplexities and find that single-way segmented models trained on morphologically segmented data show the highest performance. Finally, we evaluate the language models on the task of predictive text entry using gold standard data and measure the average number of clicks per character and keystroke savings rate. We find that the models trained on morphologically segmented data show better scores, although with substantial room for improvement. At last, we propose the usage of morphological segmentation in order to improve the end-user experience while using predictive text and we plan on testing this assumption by doing end-user evaluation.

Premium content

Machine-to-machine communication: Do we need it? What should it be like? Is it "language"?

Downloads

Next from COLING 2022

Quantifying Discourse Support for Omitted Pronouns

Similar lecture

Evaluating a Joint Training Approach for Learning Cross-lingual Embeddings with Sub-word Information without Parallel Corpora on Lower-resource Languages

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES