Papers by Kevin Knight

18 papers
Modeling Naive Psychology of Characters in Simple Commonsense Stories (P18-1)

Copied to clipboard

Challenge: Understanding a narrative requires reasoning about the causal links between the events in the story and the mental states of the characters, even when those relationships are not explicitly stated.
Approach: They propose a new annotation framework to explain naive psychology of story characters as fully-specified chains of mental states with respect to motivations and emotional reactions.
Outcome: The proposed framework provides a baseline performance on several new tasks suggesting avenues for future research.
ELISA-EDL: A Cross-lingual Entity Extraction, Linking and Localization System (N18-5)

Copied to clipboard

Challenge: ELISA-EDL is a cross-lingual entity extraction, linking and localization system for Wikipedia languages.
Approach: They propose a cross-lingual entity extraction, linking and localization system for English speakers . it extracts entities from unstructured text in any of 282 Wikipedia languages and links them to English knowledge bases .
Outcome: The proposed system extracts entity mentions from Wikipedia and links them to English knowledge bases and visualizes locations related to disaster topics on a world heatmap.
Learning to Pronounce Chinese Without a Pronunciation Dictionary (2020.emnlp-main)

Copied to clipboard

Challenge: EM method achieves a test-set accuracy of 71%, vector-based method achieve 81%.
Approach: They propose a program that learns to pronounce Chinese text in Mandarin without a pronunciation dictionary.
Outcome: The proposed program deciphers Chinese text in Mandarin without a pronunciation dictionary.
AMR Beyond the Sentence: the Multi-sentence AMR corpus (C18-1)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) is limited to capturing the semantics of individual sentences.
Approach: They propose a corpus that annotates coreference and similar phenomena on top of existing AMRs.
Outcome: The proposed corpus is compared with existing corpora on sentence-level semantics . it shows that it can be used for information extraction and question answering .
Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation (P19-1)

Copied to clipboard

Challenge: Using a dictionary, given a rough, target language natives can uncover the latent, fully-fluent rendering of the translation.
Approach: They propose a method that breaks translation into two steps by generating a dictionary and then ‘translating’ the resulting pseudo-translation into a fully fluent translation.
Outcome: The proposed method 'gets better translation results on high-resource languages than previously published unsupervised MT studies'
Neural Poetry Translation (N18-2)

Copied to clipboard

Challenge: despite recent advances in machine translation, automatic poetry translation remains a challenging problem.
Approach: They propose a system that automatically translates a source text to an English poem . human evaluation of the translations ranks the quality as acceptable 78.2% of the time.
Outcome: The proposed system always translates a source text to an English poem. human evaluation of the translations ranks the quality as acceptable 78.2% of the time.
Paper Abstract Writing through Editing Mechanism (P18-2)

Copied to clipboard

Challenge: a paper abstract writing system can automatically generate an abstract from a title . a typical recurrent neural network (RNN) based approach easily loses focus.
Approach: They propose a paper abstract writing system that automatically generates an abstract from a title.
Outcome: The proposed system passes Turing tests by junior domain experts and non-experts at a rate up to 80%.
Leveraging Lexical Resources and Constraint Grammar for Rule-Based Part-of-Speech Tagging in Welsh (L18-1)

Copied to clipboard

Challenge: POS tags are based on pre-annotated text, but there is not enough data to train a statistical POS tagger in lesser-resourced languages such as Welsh.
Approach: They propose a rule-based POS tagger for Welsh based on the VISL Constraint Grammar parser and extract a list of possible POS tags for each word token in a running text.
Outcome: The proposed approach is particularly useful in dealing with some of the specific intricacies of Welsh, such as morphological changes and word mutations.
Out-of-the-box Universal Romanization Tool uroman (P18-4)

Copied to clipboard

Challenge: uroman converts text in Chinese, Arabic and Cyrillic into a common Latin-script representation . the tool uses string similarity metrics to compare text from different scripts .
Approach: They propose a tool that converts text in Chinese, Arabic and Cyrillic into a common Latin-script representation.
Outcome: uroman converts text in Chinese, Arabic and Cyrillic into a common Latin-script representation . the tool is available as a Perl script and as an interactive demo web page .
Abstract Meaning Representation of Constructions: The More We Include, the Better the Representation (L18-1)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) uses a flexible pattern or template of multiple lexical items to provide semantic representation of certain constructions.
Approach: They propose to expand the AMR project's lexicon of predicate senses to include entries for a growing set of constructions.
Outcome: The proposed approach provides coverage for the annotation of certain types of constructions.
Using Word Vectors to Improve Word Alignments for Low Resource Machine Translation (N18-2)

Copied to clipboard

Challenge: Using word similarities, we improve word alignments in low resource settings . word alignment is essential for statistical machine translation (MT)
Approach: They propose a method for improving word alignments using word similarities using word vectors trained on monolingual data.
Outcome: The proposed method improves word alignments in low-resource settings by improving alignments of infrequent tokens.
Recurrent Neural Networks as Weighted Language Recognizers (N18-1)

Copied to clipboard

Challenge: Recent experiments show that RNNs outperform other methods in assigning high probability to held-out English text.
Approach: They focus on the single-layer, ReLU-activation, rational-weight RNNs with softmax . they show that most problems for such RNN are undecidable .
Outcome: The proposed model outperforms other methods in assigning high probability to held-out English text.
Parallel Corpus Filtering via Pre-trained Language Models (2020.acl-main)

Copied to clipboard

Challenge: Existing methods to filter out noisy parallel sentences from web crawled data are in demand.
Approach: They propose a method to filter out noisy sentence pairs from web crawled corpora using pre-trained language models.
Outcome: The proposed method outperforms baselines and achieves state-of-the-art on two datasets.
Translating a Language You Don’t Know In the Chinese Room (P18-4)

Copied to clipboard

Challenge: In a corruption of John Searle’s famous AI thought experiment, the Chinese Room, we enable humans to translate text even if they don’t have any prior knowledge of the source language.
Approach: They propose a tool that allows humans to translate text without prior knowledge of the source language.
Outcome: The Chinese Room tool can create fluent translations with human expertise required only for the target language.
Multi-lingual Common Semantic Space Construction via Cluster-consistent Word Embedding (D18-1)

Copied to clipboard

Challenge: a new approach to multilingual word embedding is needed to achieve this goal . a multilingual common semantic space is a language-agnostic semantic continuous space .
Approach: They propose a multilingual common semantic space where words from multiple languages are mapped into a shared space so that resources and knowledge can be shared across languages.
Outcome: The proposed approach achieves 14.6% absolute F-score gain over state-of-the-art methods on cross-lingual direct transfer.
PaperRobot: Incremental Draft Generation of Scientific Ideas (P19-1)

Copied to clipboard

Challenge: a paper robot can read existing papers and create new nodes or links in the knowledge graphs.
Approach: They propose to automate the creation of new ideas by predicting links from the background KGs.
Outcome: The proposed paper automates three tasks: read existing papers, create new ideas, predict links . the paper generated abstracts, conclusion and future work sections, and new titles are chosen over human-written ones up to 30%, 24% and 12% of the time.
MeetDot: Videoconferencing with Live Translation Captions (2021.emnlp-demo)

Copied to clipboard

Challenge: MeetDot is a videoconferencing system with live translation captions overlaid on screen . currently, the system supports speech and captions in 4 languages .
Approach: They propose a videoconferencing system with live translation captions overlaid on screen . the system supports speech and captions in 4 languages and combines automatic speech recognition and machine translation in a cascade .
Outcome: The proposed system supports speech and captions in 4 languages and has very tight latency requirements to have acceptable call quality.
Solving Historical Dictionary Codes with a Neural Language Model (2020.emnlp-main)

Copied to clipboard

Challenge: a dictionary-based substitution code is common, but no automatic decipherment algorithms exist.
Approach: They propose a decoding lattice and a neural language model to solve word-based substitution codes . they apply their method to letters exchanged between general James Wilkinson and agents of the Spanish Crown .
Outcome: The proposed method decrypts letters written by general James Wilkinson and agents of the Spanish Crown in the late 1700s and early 1800s using a neural language model.

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