Skip to search formSkip to main contentSkip to account menu

PAWS: Paraphrase Adversaries from Word Scrambling

PAWS (Paraphrase Adversaries from Word Scrambling), a new dataset with 108,463 well-formed paraphrase and non-paraphrase pairs with high lexical overlap, is introduced, providing an effective instrument for driving further progress on models that better exploit structure, context, and pairwise comparisons.
View on ACL (opens in a new tab)

PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification

PAWS-X, a new dataset of 23,659 human translated PAWS evaluation pairs in six typologically distinct languages, shows the effectiveness of deep, multilingual pre-training while also leaving considerable headroom as a new challenge to drive multilingual research that better captures structure and contextual information.
View on ACL (opens in a new tab)

Mind the GAP: A Balanced Corpus of Gendered Ambiguous Pronouns

GAP, a gender-balanced labeled corpus of 8,908 ambiguous pronoun–name pairs sampled, is presented and released to provide diverse coverage of challenges posed by real-world text and shows that syntactic structure and continuous neural models provide promising, complementary cues for approaching the challenge.
View on ACL (opens in a new tab)

Supervised Text-based Geolocation Using Language Models on an Adaptive Grid

The adaptive grid achieves competitive results with a uniform grid on small training sets and outperforms it on the large Twitter corpus and the two grid constructions can also be combined to produce consistently strong results across all training sets.
View on ACL (opens in a new tab)

Twitter Polarity Classification with Label Propagation over Lexical Links and the Follower Graph

Results on polarity classification for several datasets show that the label propagation approach rivals a model supervised with in-domain annotated tweets, and it outperforms the noisily supervised classifier it exploits as well as a lexicon-based polarity ratio classifier.
View on ACL (opens in a new tab)

Simple supervised document geolocation with geodesic grids

This work investigates automatic geolocation (i.e. identification of the location, expressed as latitude/longitude coordinates) of documents and describes several simple supervised methods for document geolocated using only the document's raw text as evidence.
View on ACL (opens in a new tab)

Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation

This work highlights shortcomings of current metrics for the Room-to-Room dataset and proposes a new metric, Coverage weighted by Length Score (CLS), and shows that agents that receive rewards for instruction fidelity outperform agents that focus on goal completion.
View on ACL (opens in a new tab)

Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

The Pathways Autoregressive Text-to-Image (Parti) model is presented, which generates high-fidelity photorealistic images and supports content-rich synthesis involving complex compositions and world knowledge and explores and highlights limitations of the models.
View PDF on arXiv (opens in a new tab)

Lexically specified derivational control in combinatory categorial grammar

This dissertation elaborates several refinements to the Combinatory Categorial Grammar (ccg) framework, and shows how the multi-modal perspective on grammatical composition provided by the logical tradition of categorial grammar can be incorporated into ccg’s rulebased approach.

Combinatory Categorial Grammar

Combinatory Categorial Grammar is a generalization of classical Categorial Grammar that is at the least greater level of expressive power than context-free grammar that has yet been identified. The…
View via Publisher (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)