about ▽
Hi, please visit my new website.
news ▽
Mar: I'll be returning to Microsoft Semantic Machines as a research scientist, starting late summer!
Feb: paper on annotating coref with active learning accepted to ACL.
papers ▽
Pruning Pretrained Encoders with a Multitask Objective
Patrick Xia, Richard ShinIn ENLSP at NeurIPS (2021)
= pdf =
On Generalization in Coreference Resolution
Shubham Toshniwal*, Patrick Xia*, Sam Wiseman, Kevin Gimpel, Karen LivescuIn CRAC (2021) [best short paper]
= pdf code =
Moving on from OntoNotes: Coreference Resolution Model Transfer
Patrick Xia, Benjamin Van DurmeIn EMNLP (2021)
= pdf code slides (pdf, ppt) poster =
Adaptive Active Learning for Coreference Resolution
Michelle Yuan, Patrick Xia, Benjamin Van Durme, Jordan Boyd-GraberarXiv (2021)
= pdf =
LOME: Large Ontology Multilingual Extraction
Patrick Xia*, Guanghui Qin*, Siddharth Vashishtha, Yunmo Chen, Tongfei Chen, Chandler May, Craig Harman, Kyle Rawlins, Aaron Steven White, Benjamin Van DurmeIn EACL System Demonstrations (2021)
= webpage pdf slides (pdf, ppt) poster Docker =
CopyNext: Explicit Span Copying and Alignment in Sequence to Sequence Models
Abhinav Singh, Patrick Xia, Guanghui Qin, Mahsa Yarmohammadi, Benjamin Van DurmeIn SPNLP (2020) [spotlight talk]
= pdf code =
Which *BERT? A Survey Organizing Contextualized Encoders
Patrick Xia, Shijie Wu, Benjamin Van Durme In EMNLP (2020)= pdf slides (pdf (long), pdf (short), ppt) video =
Incremental Neural Coreference Resolution in Constant Memory
Patrick Xia, João Sedoc, Benjamin Van Durme In EMNLP (2020)= pdf slides (pdf, ppt) code video =
Multi-Sentence Argument Linking
Seth Ebner*, Patrick Xia*, Ryan Culkin, Kyle Rawlins, Benjamin Van Durme In ACL (2020)= pdf data code slides (ppt, pdf) =
Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling
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Katherin Yu, Shuning Jin, Berlin Chen, Benjamin Van Durme, Edouard Grave, Ellie Pavlick, Sam Bowman In ACL (2019)= (outdated) OpenReview (outdated) arXiv pdf code =
Probing What Different NLP Tasks Teach Machines about Function Word Comprehension
Najoung Kim, Roma Patel, Adam Poliak, Patrick Xia, Alex Wang, Tom McCoy, Ian Tenney, Alexis Ross, Tal Linzen, Benjamin Van Durme, Sam Bowman and Ellie PavlickIn *SEM (2019) [best paper]
= pdf code =
Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting
J. Edward Hu, Huda Khayrallah, Ryan Culkin, Patrick Xia, Tongfei Chen, Matt Post and Benjamin Van DurmeIn NAACL (2019)
= pdf demo website paraphrased MNLI =
What do you learn from context? Probing for sentence structure in contextualized word representations
Ian Tenney, Patrick Xia, Berlin Chen, Alex Wang, Adam Poliak, R Thomas McCoy, Najoung Kim, Benjamin Van Durme, Sam Bowman, Dipanjan Das, Ellie PavlickIn ICLR (2019)
= OpenReview pdf related slides poster code =
Consensus for Multi-Parallel Corpora: An English Bible Study
Patrick Xia and David YarowskyIn IJCNLP (2017)
= pdf slides code =
CoNLL-SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection in 52 Languages
Ryan Cotterell, Christo Kirov, John Sylak-Glassman, Géraldine Walther, Ekaterina Vylomova, Patrick Xia, Manaal Faruqui, Sandra Kübler, David Yarowsky, Jason Eisner, and Mans HuldenIn CONLL (2017)
= pdf website =
Annotating Character Relationships in Literary Texts
Philip Massey, Patrick Xia, David Bamman, Noah A. SmitharXiv (2015)
= pdf =
puzzles ▽
I've been writing puzzles since ~2013, starting with PuzzlehuntCMU, and more recently with Galactic Puzzle Hunt and Teammate Hunt. This list contains some recent standalone puzzles; a more complete list can be found here.
Puzzle |
Event |
Solution |
Symbols | Galactic Puzzle Hunt (2021) | Solution |
Thrifty/Thrifty | Galactic Puzzle Hunt (2021) | Solution |
Drip Quote | Teammate Hunt (2020) | Solution |
Connect the Dots | Teammate Hunt (2020) | Solution |
This Anagram Does Not Exist | Teammate Hunt (2020) | Solution |
50/50 | Galactic Puzzle Hunt (2019) | Solution |
Now Get Ready For... | Galactic Puzzle Hunt (2018) | Solution |
Fan Video | Puzzlehunt CMU (2016) | Solution |
Chromesthesia | Puzzlehunt CMU (2016) | Solution |
random stuff ▽
projects ▽
Fun projects from the last several years:
Puflantu
- (2019), a conlang created by several of the puzzle authors for Galactic Puzzlehunt.
shallow
- (2018-2020) a Discord bot for puzzles and various other information-retrieval ish tasks.
codenames
- (2016) a simple word vector implementation of a codenames game AI
this website
- (2016-now) a from-scratch attempt to construct something in CSS/HTML
Translating into Morphologically Rich Languages
(Senior Honors Thesis) - (2016) learning morphology with LSTMs + context
M-pathery
(15-418 final project) - (2016) monte carlo tree search solver for pathery (github)presentations ▽
These are presentations I made of other people's work, often for reading groups.
An incomplete snapshot of multi-hop inference (@ EMNLP 2021)
Presented at TeCho Reading Group November 2021This is a survey over several papers that all relate to multi-hop inference or multi-hop reasoning that were all published at EMNLP 2021
= slides =
Reformer: The Efficient Transformer (ICLR 2020)
Authors: Nikita Kitaev, Lukasz Kaiser, Anselm LevskayaPresented at JHU NLP Reading Group April 2020
This is a presentation of the Reformer model, a paper that was published at ICLR 2020
= paper slides =
(Very) Recent Ideas in Pretrained Contextualized Language Representations
Presented at TeCho Reading Group October 2019This is a survey on pretrained language models covering BERT, RoBERTa, SpanBERT, etc. These slides were eventually written up into a EMNLP 2020 paper.
= slides =notes ▽
Some other random notes I've taken on language, computer science, machine learning, and math.