Supervised attention method with co-reference resolution for aspect extraction
Ganpat Singh Chauhan, Shalini Puri, Ravi Nahta, Neeraj Garg · 2026
Read Supervised attention method with co-reference resolution for aspect extraction by Ganpat Singh Chauhan, Shalini Puri, Ravi Nahta, Neeraj Garg (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13391493.txt.
Description
Ganpat Singh Chauhan, Shalini Puri, Ravi Nahta, and Neeraj Garg improve aspect extraction from reviews in a 2026 paper. Aspect based sentiment work tries to find which features of a product or place each opinion targets.
Reviews spread judgments across sentences, and pronouns can hide which aspect is meant. Their model first resolves those references so the sentences line up in meaning. A two level attention network then reads words and sentences in turn to tag the aspects, using word vectors enriched with context. On standard laptop and restaurant review sets, the model beat strong baselines and recent methods. Gains over a graph based rival were clear in the F score.
Catalog record
| CREATOR | Ganpat Singh Chauhan, Shalini Puri, Ravi Nahta, Neeraj Garg |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 107 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |