• Publications
  • Influence
Robust Disambiguation of Named Entities in Text
TLDR
A robust method for collective disambiguation is presented, by harnessing context from knowledge bases and using a new form of coherence graph that significantly outperforms prior methods in terms of accuracy, with robust behavior across a variety of inputs.
Grounding Action Descriptions in Videos
TLDR
A general purpose corpus is presented that aligns high quality videos with multiple natural language descriptions of the actions portrayed in the videos, together with an annotation of how similar the action descriptions are to each other.
Contextualizing Semantic Representations Using Syntactically Enriched Vector Models
TLDR
A syntactically enriched vector model that supports the computation of contextualized semantic representations in a quasi compositional fashion is presented and substantially outperforms previous work on a paraphrase ranking task and achieves promising results on a wordsense similarity task.
Translating Video Content to Natural Language Descriptions
TLDR
This paper generates a rich semantic representation of the visual content including e.g. object and activity labels and proposes to formulate the generation of natural language as a machine translation problem using the semantic representation as source language and the generated sentences as target language.
What Substitutes Tell Us - Analysis of an "All-Words" Lexical Substitution Corpus
TLDR
The nature of lexical substitute sets are investigated, finding them to be consistent with, but more fine-grained than, synsets, which highlights the influence of corpus construction approaches on evaluation results.
MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge
TLDR
A large dataset of narrative texts and questions about these texts, intended to be used in a machine comprehension task that requires reasoning using commonsense knowledge, and shows that the mode of data collection via crowdsourcing results in a substantial amount of inference questions.
SemEval-2018 Task 11: Machine Comprehension Using Commonsense Knowledge
TLDR
This report summarizes the results of the SemEval 2018 task on machine comprehension using commonsense knowledge, where the best performing system achieves an accuracy of 83.95%, outperforming the baselines by a large margin, but still far from the human upper bound, which was found to be at 98%.
Word Meaning in Context: A Simple and Effective Vector Model
TLDR
A model that represents word meaning in context by vectors which are modified according to the words in the target’s syntactic context, which outperforms all previous models on a word sense disambiguation task.
Bridging the gap between underspecification formalisms: hole semantics as dominance constraints
TLDR
This work defines a back-and-forth translation between Hole Semantics and dominance constraints, two formalisms used in underspecified semantics and shows that they disappear on practically useful descriptions.
A Crowdsourced Database of Event Sequence Descriptions for the Acquisition of High-quality Script Knowledge
TLDR
A large-scale crowdsourced collection of explicit linguistic descriptions of script-specific event sequences is presented, enriched with crowdsourced alignment annotation on a subset of the event descriptions, to be used in future work as seed data for automatic alignment of event descriptions (for example via clustering).
...
1
2
3
4
5
...