ACL Best Papers CollectingThe Annual Meeting of the Association for Computational Linguistics is the highest conference in the field of natural language processing and Computational Linguistics. It is held every year.
Emily M. Bender, Alexander Koller
ACL, pp.5185-5198, (2020)
We have argued that in contrast to some current hype, meaning cannot be learned from form alone. This means that even large language models such as BERT do not learn “meaning”; they learn some reflection of meaning into the linguistic form which is very useful in applications
Cited by4BibtexViews264Links
0
0
Manling Li, Alireza Zareian, Ying Lin, Xiaoman Pan, Spencer Whitehead, Brian Chen,Bo Wu, Heng Ji, Shih-Fu Chang, Clare Voss, Daniel Napierski, Marjorie Freedman
ACL, pp.77-86, (2020)
We demonstrate a state-of-the-art multimedia multilingual knowledge extraction and event recommendation system
Cited by0BibtexViews104Links
0
0
ACL, pp.4902-4912, (2020)
Adopting principles from behavioral testing in software engineering, we propose CheckList, a model-agnostic and task-agnostic testing methodology that tests individual capabilities of the model using three different test types
Cited by0BibtexViews962Links
0
0
Wen Zhang,Yang Feng,Fandong Meng, Di You,Qun Liu
Meeting of the Association for Computational Linguistics, (2019)
We propose several strategies to improve the performance of approach on relieving the overcorrection problem, including utilizing the word-level oracle, the sentence-level oracle, and incorporating the Gumbel noise for oracle selection
Cited by19BibtexViews78Links
0
0
Nanjiang Jiang, Marie-Catherine de Marneffe
ACL (1), pp.4208-4213, (2019)
Two metrics were reported for both models: mean absolute error, measuring the absolute fit, We evaluated the models of Stanovsky et al and Rudinger et al on the CommitmentBank
Cited by3BibtexViews39
0
0
Rui Xia, Zixiang Ding
Meeting of the Association for Computational Linguistics, (2019)
We propose a new task: emotioncause pair extraction, which aims to extract potential pairs of emotions and corresponding causes in text
Cited by0BibtexViews66Links
0
0
Fabio Kepler, Jonay Trénous, Marcos Treviso, Miguel Vera,André F. T. Martins
ACL (3), pp.117-122, (2019)
OpenKiwi was adopted as the baseline system for the WMT 2019 Quality estimation shared task6, all the winning systems of the word-, sentence- and document-level tasks of the
Cited by0BibtexViews38Links
0
0
Chris Dyer, Adhiguna Kuncoro,John Hale, Jonathan Brennan
ACL, pp.2726-2735, (2018)
Cited by25BibtexViews101Links
0
0
ACL, (2017): 1182-1192
We report results for cross-entropy and the cloze evaluation in Table 1.9 Under both metrics, we see that the determinantal point process is slightly better than the Markov Point Process; both are better than the Bernoulli point process
Cited by13BibtexViews78Links
0
0
E. Dario Gutiérrez,Roger Levy,Benjamin Bergen
We proposed String-Metric Learning for Kernel Regression, a novel algorithm that can learn weighted string edit distances that minimize kernel regression error
Cited by12BibtexViews64Links
0
0
International Workshop on the ACL2 Theorem Prover and Its Applications, (2015)
We provide an alternate mechanism, and since the Pearson correlation is a unit-free measure, it can be applied to evaluation of quality estimation systems avoiding the previous vulnerabilities of measures such as mean absolute error and root mean squared error
Cited by26BibtexViews48Links
0
0
International Workshop on the ACL2 Theorem Prover and Its Applications, (2015)
By learning to dynamically select the most predictive features at test time, our algorithm provides significant speed improvements to classifier-based structured prediction algorithms, which themselves already comprise the fastest methods in NLP
Cited by16BibtexViews89Links
0
0
ACL, pp.1370-1380, (2014)
We have described a novel formulation for a neural network-based machine translation joint model, along with several simple variations of this model
Cited by437BibtexViews231Links
0
0
ACL, pp.53-63, (2013)
We presented a method that learns word meanings from video paired with sentences
Cited by129BibtexViews58Links
0
0
ACL, (2012)
We have presented an SR-tree substitution grammar, which is an extension of the conventional TSG model where each symbol of tree fragments can be automatically subcategorized to address the problem of the conditional independence assumptions of a TSG
Cited by55BibtexViews56Links
0
0
ACL, pp.449-458, (2012)
Experimental results show that kb-string rewriting kernel achieve better results than state-of-the-art methods on paraphrase identification and recognizing textual entailment
Cited by11BibtexViews77Links
0
0
ACL, pp.600-609, (2011)
We have shown the efficacy of graph-based label propagation for projecting part-of-speech information across languages
Cited by291BibtexViews75Links
0
0
ACL, pp.1583-1592, (2010)
We have presented a preliminary study of implicit arguments for nominal predicates that focused on this problem
Cited by115BibtexViews59Links
0
0
ACL/IJCNLP, pp.82-90, (2009)
We showed that having access to a suitable reward function can significantly reduce the need for annotations
Cited by210BibtexViews66Links
0
0
ACL/IJCNLP, pp.342-350, (2009)
We presented new dependency parsers based on concise integer linear programming formulations
Cited by189BibtexViews75Links
0
0