Papers by Patrick Xia
Multi-Sentence Argument Linking (2020.acl-main)
Copied to clipboard
| Challenge: | Existing datasets for cross-sentence linking are small, resulting in a lack of a model for argument linking. |
| Approach: | They propose a document-level model for finding argument spans that fill an event’s roles by combining semantic role labeling and coreference resolution. |
| Outcome: | The proposed model is able to connect arguments in sentence-level role labeling and coreference resolution on 9,124 annotated events across 139 types. |
Language-to-Code Translation with a Single Labeled Example (2024.emnlp-main)
Copied to clipboard
Kaj Bostrom, Harsh Jhamtani, Hao Fang, Sam Thomson, Richard Shin, Patrick Xia, Benjamin Van Durme, Jason Eisner, Jacob Andreas
| Challenge: | In-Context Inverse Programming (ICIP) bootstraps a language-to-code system using mostly unlabeled programs written using a potentially unfamiliar library or API. |
| Approach: | They propose a method for bootstrapping a language-to-code system using mostly unlabeled programs written using a potentially unfamiliar library or API. |
| Outcome: | The proposed method outperforms baselines across nine domains and 100 examples in a “nearly unsupervised” setting. |
Interpreting User Requests in the Context of Natural Language Standing Instructions (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to LLM-based dialogue modeling provide additional context for users to make requests. |
| Approach: | They propose an approach to LLM-based dialogue modeling where persistent user constraints and preferences are provided as additional context for such interfaces. |
| Outcome: | The proposed model achieves a maximum of 46% exact match on the prediction of 2.4K English dialogues with a language-to-program dataset. |
Automatic Document Selection for Efficient Encoder Pretraining (2022.emnlp-main)
Copied to clipboard
| Challenge: | Pretraining language models is expensive and data-intensive, but can it be improved? Several studies have found that directly pretraining on task data is more effective . |
| Approach: | They propose to automatically identify smaller yet domain-representative subsets by pretraining a model on a target domain. |
| Outcome: | The proposed method outperforms random selection on perplexity and downstream tasks with 20x less data and 3x fewer training iterations and 2x less estimated cloud compute cost. |
Multilingual Coreference Resolution in Multiparty Dialogue (2023.tacl-1)
Copied to clipboard
| Challenge: | Existing datasets for entity coreference resolution are limited to English and other languages are rare. |
| Approach: | They propose to use TV transcripts to create multilingual multiparty coreference datasets that leverage existing subtitles in Chinese and Farsi. |
| Outcome: | The proposed dataset re-annotates for coreference on TV transcripts and then leverages existing subtitle translations to create a multilingual corpus. |
UniMorph 2.0: Universal Morphology (L18-1)
Copied to clipboard
Christo Kirov, Ryan Cotterell, John Sylak-Glassman, Géraldine Walther, Ekaterina Vylomova, Patrick Xia, Manaal Faruqui, Sabrina J. Mielke, Arya McCarthy, Sandra Kübler, David Yarowsky, Jason Eisner, Mans Hulden
| Challenge: | The Universal Morphology project is a collaborative effort to improve how NLP handles complex morphology across the world's languages. |
| Approach: | They propose to use a universal tagset to annotate morphological data using a schema that includes a lemma and a bundle of morphology features. |
| Outcome: | The project releases annotated morphological data using a universal tagset, the UniMorph schema. |
Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling (P19-1)
Copied to clipboard
Alex Wang, Jan Hula, Patrick Xia, Raghavendra Pappagari, R. Thomas McCoy, Roma Patel, Najoung Kim, Ian Tenney, Yinghui Huang, Katherin Yu, Shuning Jin, Berlin Chen, Benjamin Van Durme, Edouard Grave, Ellie Pavlick, Samuel R. Bowman
| Challenge: | State-of-the-art models in natural language processing (NLP) often incorporate sentence encoder functions which generate a sequence of vectors intended to represent the in-context meaning of each word in an input text. |
| Approach: | They conduct the first large-scale systematic study of candidate pretraining tasks, comparing 19 different tasks as alternatives and complements to language modeling. |
| Outcome: | The proposed model can be used to train sentences on language modeling tasks. |
LOME: Large Ontology Multilingual Extraction (2021.eacl-demos)
Copied to clipboard
Patrick Xia, Guanghui Qin, Siddharth Vashishtha, Yunmo Chen, Tongfei Chen, Chandler May, Craig Harman, Kyle Rawlins, Aaron Steven White, Benjamin Van Durme
| Challenge: | LOME is a system for performing multilingual information extraction with large ontologies. |
| Approach: | They propose a system for multilingual information extraction with a framenet parser . LOME is available as a Docker container on Docker Hub and a lightweight version is available on the web . |
| Outcome: | The proposed system outperforms or is competitive with the (monolingual) state-of-the-art . it can be used to build knowledge graphs with large ontologies and across multiple languages . |
Learning to Retrieve Iteratively for In-Context Learning (2024.emnlp-main)
Copied to clipboard
Yunmo Chen, Tongfei Chen, Harsh Jhamtani, Patrick Xia, Richard Shin, Jason Eisner, Benjamin Van Durme
| Challenge: | In-context learning is a powerful tool for learning large language models. |
| Approach: | They propose an iterative retrieval framework that empowers retrievers to make iterable decisions through policy optimization. |
| Outcome: | The proposed framework outperforms existing methods on semantic parsing datasets with 4M additional parameters for state encoding. |
Adapting Coreference Resolution Models through Active Learning (2022.acl-long)
Copied to clipboard
| Challenge: | Neural coreference resolution models trained on one dataset may not transfer to new, low-resource domains. |
| Approach: | They investigate how to actively label coreference by sampling a small subset of data for annotators to label. |
| Outcome: | The proposed model can be more realistic when labeling spans within the same document than when annotating spans across documents. |
Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting (N19-1)
Copied to clipboard
J. Edward Hu, Huda Khayrallah, Ryan Culkin, Patrick Xia, Tongfei Chen, Matt Post, Benjamin Van Durme
| Challenge: | Lexically-constrained sequence decoding allows for explicit positive or negative phrase-based constraints to be placed on target output strings in machine translation or monolingual text rewriting tasks. |
| Approach: | They propose a vectorized dynamic beam allocation algorithm which extends work in lexically-constrained decoding to work with batching. |
| Outcome: | The proposed method improves on natural language inference, question answering and machine translation tasks by fivefold . |
Incremental Neural Coreference Resolution in Constant Memory (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on coreference resolution has focused on improving pairwise span scoring functions and methods for decoding into globally consistent clusters. |
| Approach: | They extend an incremental clustering algorithm to utilize contextualized encoders and neural components to generate a high-performing model. |
| Outcome: | The proposed model reduces memory usage to constant space with only a 0.3% relative loss in F1 on OntoNotes 5.0. |
Which *BERT? A Survey Organizing Contextualized Encoders (2020.emnlp-main)
Copied to clipboard
| Challenge: | a survey on language representation learning aims to highlight common themes . we focus on the areas of progress, compared to other fields, and discuss how each area is evaluated. |
| Approach: | They present a survey on language representation learning to highlight common themes . they compare contributions in contextualized text encoders to ideas from other fields . |
| Outcome: | The proposed survey aims to highlight common themes in the field of language representation learning. |
Moving on from OntoNotes: Coreference Resolution Model Transfer (2021.emnlp-main)
Copied to clipboard
| Challenge: | Academic neural models for coreference resolution (coref) are typically trained on OntoNotes and model improvements are benchmarked on that dataset. |
| Approach: | They aim to quantify transferability of coref models based on the number of annotated documents available in the target dataset. |
| Outcome: | The proposed model improvements are consistent with the state-of-the-art results on PreCo. |
UniMorph 3.0: Universal Morphology (2020.lrec-1)
Copied to clipboard
Arya D. McCarthy, Christo Kirov, Matteo Grella, Amrit Nidhi, Patrick Xia, Kyle Gorman, Ekaterina Vylomova, Sabrina J. Mielke, Garrett Nicolai, Miikka Silfverberg, Timofey Arkhangelskiy, Nataly Krizhanovsky, Andrew Krizhanovsky, Elena Klyachko, Alexey Sorokin, John Mansfield, Valts Ernštreits, Yuval Pinter, Cassandra L. Jacobs, Ryan Cotterell, Mans Hulden, David Yarowsky
| Challenge: | Explicit modeling of morphology has demonstrable benefits for language modeling, speech recognition, word embedding and keyword search. |
| Approach: | They propose a language-independent feature schema for rich morphological annotation and a type-level resource for annotated data in diverse languages. |
| Outcome: | The proposed schema has been improved to make it more complete and correct, and adds 66 new languages and parts of speech for 12 languages. |
Choosing Transfer Languages for Cross-Lingual Learning (P19-1)
Copied to clipboard
Yu-Hsiang Lin, Chian-Yu Chen, Jean Lee, Zirui Li, Yuyan Zhang, Mengzhou Xia, Shruti Rijhwani, Junxian He, Zhisong Zhang, Xuezhe Ma, Antonios Anastasopoulos, Patrick Littell, Graham Neubig
| Challenge: | Cross-lingual transfer is a useful tool for improving performance of natural language processing (NLP) on low-resource languages. |
| Approach: | They propose to use cross-lingual transfer to improve accuracy of low-resource languages . they build models that consider features to perform prediction on such languages based on ranking problem . |
| Outcome: | The proposed model predicts good transfer languages much better than baselines considering single features in isolation. |