1 |
Decontextualization: Making Sentences Stand-Alone ...
|
|
|
|
Abstract:
Models for question answering, dialogue agents, and summarization often interpret the meaning of a sentence in a rich context and use that meaning in a new context. Taking excerpts of text can be problematic, as key pieces may not be explicit in a local window. We isolate and define the problem of sentence decontextualization: taking a sentence together with its context and rewriting it to be interpretable out of context, while preserving its meaning. We describe an annotation procedure, collect data on the Wikipedia corpus, and use the data to train models to automatically decontextualize sentences. We present preliminary studies that show the value of sentence decontextualization in a user facing task, and as preprocessing for systems that perform document understanding. We argue that decontextualization is an important subtask in many downstream applications, and that the definitions and resources provided can benefit tasks that operate on sentences that occur in a richer context. ... : To appear in Transactions of the Association for Computational Linguistics (TACL) ...
|
|
Keyword:
Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2102.05169 https://arxiv.org/abs/2102.05169
|
|
BASE
|
|
Hide details
|
|
3 |
Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
QED: A Framework and Dataset for Explanations in Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
QED: A Framework and Dataset for Explanations in Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Natural Questions: A Benchmark for Question Answering Research
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 7, Pp 453-466 (2019) (2019)
|
|
BASE
|
|
Show details
|
|
9 |
Predicting the impact of scientific concepts using full‐text features
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Learning Dictionaries for Named Entity Recognition using Minimal Supervision ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Experiments With Spectral Learning of Latent-Variable PCFGs
|
|
|
|
In: Statistics Papers (2013)
|
|
BASE
|
|
Show details
|
|
13 |
Cognitive Perspectives On English Word Order
|
|
|
|
In: http://rave.ohiolink.edu/etdc/view?acc_num=osu1343315752 (2012)
|
|
BASE
|
|
Show details
|
|
14 |
They do be anxious about their speech: Performance and Perceptions of Authenticity in Irish-Newfoundland English
|
|
|
|
In: The English Languages: History, Diaspora, Culture; Vol 3 (2012) ; 1929-5855 (2012)
|
|
BASE
|
|
Show details
|
|
15 |
Depth and distance perception of dentists and dental students
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Dialect Recognition Using a Phone-GMM-Supervector-Based SVM Kernel: Presentation Slides
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Dialect Recognition Using a Phone-GMM-Supervector-Based SVM Kernel
|
|
|
|
BASE
|
|
Show details
|
|
19 |
On dual decomposition and linear programming relaxations for natural language processing
|
|
|
|
In: MIT web domain (2010)
|
|
BASE
|
|
Show details
|
|
20 |
Dual decomposition for parsing with non-projective head automata
|
|
|
|
In: MIT web domain (2010)
|
|
BASE
|
|
Show details
|
|
|
|