Papers by Kevin Tang

11 papers
Playing with Voices: Tabletop Role-Playing Game Recordings as a Diarization Challenge (2025.findings-naacl)

Copied to clipboard

Challenge: Using a small dataset, we propose that audio of tabletop role-playing games (TTRPGs) could serve as a challenge for speaker diarization systems.
Approach: They propose that audio of tabletop role-playing games (TTRPGs) could serve as a challenge for speaker diarization systems.
Outcome: The proposed system can pick the speaker and determine that impersonating is just that.
One Agent To Rule Them All: Towards Multi-agent Conversational AI (2022.findings-acl)

Copied to clipboard

Challenge: Increasing volume of conversational agents (CAs) on the market has resulted in users being burdened with learning and adopting multiple agents to accomplish their tasks.
Approach: They propose a task BBAI: Black-Box Agent Integration that integrates multiple black-box CAs at scale.
Outcome: The proposed system outperforms existing benchmarks in the BBAI: Black-Box Agent Integration task.
A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations (N19-1)

Copied to clipboard

Challenge: Empirically, the model with the best performing syntactic and semantic representations gives rise to the most disentangled representations.
Approach: They propose a generative model that uses latent variables to learn a sentence that uses both latent and latent representations.
Outcome: The proposed model achieves better disentanglement between semantic and syntactic representations by training with multiple losses, including losses that exploit aligned paraphrastic sentences and word-order information.
An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction (D19-1)

Copied to clipboard

Challenge: Task-oriented dialog systems need to know when a query falls outside their range of supported intents.
Approach: They propose a dataset that includes queries that are out-of-scope and 150 intent classes over 10 domains.
Outcome: The proposed dataset includes queries that are out-of-scope, i.e., queries that do not fall into any of the system’s supported intents.
Predicting Language Models’ Success at Zero-Shot Probabilistic Prediction (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent work has investigated the capabilities of large language models (LLMs) as zero-shot models for generating individual-level characteristics.
Approach: They conduct a large-scale empirical study of large language models’ zero-shot predictive capabilities across a wide range of tabular prediction tasks.
Outcome: The results show that LLMs perform well on the base prediction task, and when they perform well, they are more likely to provide high-quality predictions.
Frequency matters: Modeling irregular morphological patterns in Spanish with Transformers (2025.findings-acl)

Copied to clipboard

Challenge: A common generation task in morphology is morphological inflection, where a target form has to be generated from its corresponding lemma and feature tag.
Approach: They propose to solve the Paradigm Cell Filling Problem (PCFP) by using encoder-decoder transformers to generate inflected verbs in Spanish.
Outcome: The proposed model performs better on L-shaped verbs than regular verbs, but no consistent recency effects are observed.
Controllable Paraphrase Generation with a Syntactic Exemplar (P19-1)

Copied to clipboard

Challenge: Prior work on controllable text generation assumes that the generated attribute can take on a finite set of values known a priori.
Approach: They propose a task where the syntax of a generated sentence is controlled rather by a sentential exemplar.
Outcome: The proposed model achieves improvements over baselines and learns to capture desirable characteristics.
Variational Sequential Labelers for Semi-Supervised Learning (D18-1)

Copied to clipboard

Challenge: a family of multitask variational methods for semi-supervised sequence labeling is currently unclear how to use them in the context of sequence labelling.
Approach: They propose a family of multitask variational methods for semi-supervised sequence labeling using latent variables and a discriminative labeler.
Outcome: The proposed models outperform standard sequential baselines on 8 sequence labeling datasets and improve further with unlabeled data.
Leveraging Syntactic Dependencies in Disambiguation: The Case of African American English (2024.lrec-main)

Copied to clipboard

Challenge: African American English (AAE) is a low-resource language facing the challenge of inadequate annotated data for training natural language processing models.
Approach: They propose a syntactically informed classifier for automatic disambiguation of AAE's habitual be.
Outcome: The proposed classifier improves automatic disambiguation of habitual and non-habitual meanings of "be" integrating syntactic information improves disambiguations of habituality by 65 F1 points over baseline models and as much as 74 points.
ParsTranslit: Truly Versatile Tajik-Farsi Transliteration (2026.findings-eacl)

Copied to clipboard

Challenge: Despite significant similarities between the two written standards, script differences hinder simple one-to-one mapping, hindering written communication and interaction between Tajikistan and its Persian-speaking “siblings”.
Approach: They propose to use a sequence-to-sequence model to convert between two scripts in a Persian-speaking country using two datasets.
Outcome: The proposed model achieves chrF++ and Normalized CER scores of 87.91 and 0.05 from Farsi to Tajik and 92.28 and 0.04 from Tajikistan to Farsis.
Analysis of LLM as a grammatical feature tagger for African American English (2025.findings-naacl)

Copied to clipboard

Challenge: African American English (AAE) presents unique challenges in natural language processing (NLP).
Approach: They evaluate the ability of different NLP systems to recognize distinctive AAE grammatical features by using sentence-level binary classification tasks using both zero-shot and fewshot strategies.
Outcome: The evaluation involved sentence-level binary classification tasks, using both zero-shot and few-shot strategies.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations