MétaCan
Menu
Back to cohort
Record W3166631396 · doi:10.1613/jair.1.13083

Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems

2022· article· en· W3166631396 on OpenAlexaff
Evgeniia Razumovskaia, Goran Glavašš, Olga Majewska, Edoardo Maria Ponti, Anna Korhonen, Ivan Vulić

Bibliographic record

VenueJournal of Artificial Intelligence Research · 2022
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsMcGill UniversityMila - Quebec Artificial Intelligence Institute
Fundersnot available
KeywordsComputer scienceTask (project management)Pipeline (software)Natural language processingFocus (optics)Machine translationArtificial intelligenceModular designConversationPoint (geometry)Field (mathematics)LinguisticsProgramming language

Abstract

fetched live from OpenAlex

In task-oriented dialogue (ToD), a user holds a conversation with an artificial agent with the aim of completing a concrete task. Although this technology represents one of the central objectives of AI and has been the focus of ever more intense research and development efforts, it is currently limited to a few narrow domains (e.g., food ordering, ticket booking) and a handful of languages (e.g., English, Chinese). This work provides an extensive overview of existing methods and resources in multilingual ToD as an entry point to this exciting and emerging field. We find that the most critical factor preventing the creation of truly multilingual ToD systems is the lack of datasets in most languages for both training and evaluation. In fact, acquiring annotations or human feedback for each component of modular systems or for data-hungry end-to-end systems is expensive and tedious. Hence, state-of-the-art approaches to multilingual ToD mostly rely on (zero- or few-shot) cross-lingual transfer from resource-rich languages (almost exclusively English), either by means of (i) machine translation or (ii) multilingual representations. These approaches are currently viable only for typologically similar languages and languages with parallel / monolingual corpora available. On the other hand, their effectiveness beyond these boundaries is doubtful or hard to assess due to the lack of linguistically diverse benchmarks (especially for natural language generation and end-to-end evaluation). To overcome this limitation, we draw parallels between components of the ToD pipeline and other NLP tasks, which can inspire solutions for learning in low-resource scenarios. Finally, we list additional challenges that multilinguality poses for related areas (such as speech, fluency in generated text, and human-centred evaluation), and indicate future directions that hold promise to further expand language coverage and dialogue capabilities of current ToD systems.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.008
metaresearch head score (Gemma)0.010
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Review · Consensus signal: none
Teacher disagreement score0.009
Threshold uncertainty score0.043

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0080.010
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0050.004
Science and technology studies0.0010.007
Scholarly communication0.0090.022
Open science0.0050.006
Research integrity0.0050.009
Insufficient payload (model declined to judge)0.0070.005

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.145
GPT teacher head0.425
Teacher spread0.280 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreReview

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations36
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueJournal of Artificial Intelligence ResearchSame topicTopic ModelingFrench-language works237,207