Papers by Kevin Tang
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
Christopher Clarke, Joseph Peper, Karthik Krishnamurthy, Walter Talamonti, Kevin Leach, Walter Lasecki, Yiping Kang, Lingjia Tang, Jason Mars
| 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
Stefan Larson, Anish Mahendran, Joseph J. Peper, Christopher Clarke, Andrew Lee, Parker Hill, Jonathan K. Kummerfeld, Kevin Leach, Michael A. Laurenzano, Lingjia Tang, Jason Mars
| 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
Kevin Ren, Santiago Cortes-Gomez, Carlos Miguel Patiño, Ananya Joshi, Ruiqi Lyu, Jingjing Tang, Alistair Turcan, Khurram Yamin, Steven Wu, Bryan Wilder
| 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. |