Chaitanya Malaviya

Ideas Mova took (1)

From the ideas ledger: an idea tried, kept or queued, or measured with no gain, and what it gave.

• measured, no gain — Tag-conditioned lemma rules in en/src/morph.rs: when the dictionary has several candidates or a suffix rule is ambiguous, choose the rule with the UPOS and FEATS predicted by en/src/ud.rs; measure lemma accuracy on EWT dev, reporting ambiguous tokens (more… (A Simple Joint Model for Improved Contextual Neural… · lemma by predicted UPOS and relation: EWT dev lemmas 96.67 -> 96.68 (3 tokens); ambiguous forms 97.66% vs the rest 95.67% (split kept in ud-eval EN_UD_DEBUG)…)

Papers

1. AmbiCoref: Evaluating Human and Model Sensitivity to Ambiguous Coreference (2023)
   The paper asks whether coreference models react to pronoun ambiguity as people do. It builds AmbiCoref, a corpus of minimal sentence pairs: an ambiguous and an unambiguous sentence differ only in one verb phrase (for example "Abby told Brittney that she upset Courtney" against "hugged"). The templates come from four…
2. Abductive Commonsense Reasoning (2019)
   The paper introduces abductive reasoning over narratives. Given two observations O1 and O2, a system must pick the more plausible explanation from two hypotheses (αNLI), or generate one (αNLG). The ART dataset has about 20k contexts taken from ROCStories and over 200k hypotheses, written by crowdworkers and then…
3. A Simple Joint Model for Improved Contextual Neural Lemmatization (2019)
   Lemmatization maps an inflected form to its citation form, and the right lemma often depends on context, as "running" is a verb in one sentence and a noun in another.

Co-authors (12)

• Ari Holtzman
• Chandra Bhagavatula
• Doug Downey
• Hannah Rashkin
• Keisuke Sakaguchi
• Mark Yatskar
• Ronan Le Bras
• Ryan Cotterell
• Scott Wen-tau Yih
• Shijie Wu
• Yejin Choi
• Yuewei Yuan

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/chaitanya-malaviya/