Mova0.5 pre-release⌕
☰
home / docs / papers / authors / Noah A. Smith

Noah A. Smith

13 paper cards in Mova's library · 2009–2020

Noah A. Smith wrote 13 of the papers Mova reads, in 2009–2020, most of them on Dependency parsing, Machine translation, Universal Dependencies; often with Nathan Schneider, Chris Dyer, Lingpeng Kong.

OpenAlex · ORCID · h-index 94 · 40232 citations · 486 works — openalex, 2026-10-18

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology · ORCID

Topics: Dependency parsing 2 · Machine translation 2 · Universal Dependencies 1 · Part-of-speech tagging 1

Papers

  1. Evaluating Models' Local Decision Boundaries via Contrast Sets (2020) measured
    Standard test sets come from the same distribution as the training data, so a dataset with systematic gaps or annotation artifacts lets models score well with shallow heuristics.
  2. Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning (2019)
    Quoref has over 24K span-answer questions on 4.7K Wikipedia paragraphs (about 40% film plot summaries, which mention many characters), written by crowd workers so that answering needs linking two mentions of one entity.
  3. Parsing Tweets into Universal Dependencies (2018)
    The authors extend the UD guidelines to tweets: emoticons and retweet markers become non-syntactic or discourse tokens, abbreviations such as "idc" stay unnormalized as single words, multiword expressions can be merged, and tweets can have several roots.
  4. Generation from Abstract Meaning Representation using Tree Transducers (2016)
    The paper generates English from AMR graphs in two steps. A breadth-first spanning tree is taken from the graph, and a weighted tree-to-string transducer turns that tree into a sentence. The transducer rules are extracted from AMR-aligned sentences: each aligned subgraph becomes a rule with argument slots for its…
  5. Transition-Based Dependency Parsing with Stack Long Short-Term Memory (2015)
    The paper introduces the stack LSTM: an LSTM with a stack pointer, so that pushes and pops take constant time and the network keeps a vector summary of the current stack contents.
  6. A Corpus and Model Integrating Multiword Expressions and Supersenses (2015)
    The paper defines one task: find lexical expressions in running text, single- or multi-word, and label the noun and verb ones with a supersense (41 coarse classes).
  7. A Dependency Parser for Tweets (2014)
    Tweets break the assumptions of newswire parsers: many tokens (retweet markers, usernames, hashtags, URLs, punctuation) have no syntactic role, a tweet can hold several utterances with their own roots, and multiword names and idioms are common.
  8. An Empirical Comparison of Parsing Methods for Stanford Dependencies (2014)
    Stanford dependencies are usually obtained by parsing to constituents and then applying head rules (c-parsing), which is slow.
  9. Comprehensive Annotation of Multiword Expressions in a Social Web Corpus (2014)
    The authors annotate every multiword expression (MWE) in a web corpus of about 55,000 words, sentence by sentence, without limiting the kinds of MWE.
  10. Turning on the Turbo: Fast Third-Order Non-Projective Turbo Parsers (2013)
    Non-projective graph parsing with third-order features (grand- and tri-siblings, head bigrams) is NP-hard, so the paper uses AD3, an accelerated dual decomposition algorithm, and extends it with specialised head automata that solve the large subproblems exactly.
  11. Coarse Lexical Semantic Annotation with Supersenses: An Arabic Case Study (2012)
    The authors reuse WordNet's supersense labels (the coarse lexicographer classes) as a light scheme for lexical semantics, and apply it to Arabic.
  12. Tree Edit Models for Recognizing Textual Entailments, Paraphrases, and Answers to Questions (2010)
    The paper models a pair of sentences as a sequence of tree edits between their dependency trees. Edits are insert, delete and relabel operations plus three that handle reordering: move a subtree, make a new root, and move a sibling. The sequence is found by greedy best-first search, using a normalised partial tree…
  13. Feature-Rich Translation by Quasi-Synchronous Lattice Parsing (2009)
    The paper presents a log-linear translation model that puts phrase features, target n-gram and dependency-syntax features, and tree-to-tree configuration features into one score.

Co-authors (51)

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/noah-a-smith/