Search Results for author:
Found 44 papers, 21 papers with code
When classifying grammatical role, BERT doesn’t care about word order... except when it matters
Because meaning can often be inferred from lexical semantics alone, word order is often a redundant cue in natural language.
Investigating Information-Theoretic Properties of the Typology of Spatial Demonstratives
Using data from Nintemann et al. (2020), we explore the variability in complexity and informativity across spatial demonstrative systems using spatial deictic lexicons from 223 languages.
longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks.
Developing methods to adversarially challenge NLP systems is a promising avenue for improving both model performance and interpretability.
Is It JUST Semantics? A Case Study of Discourse Particle Understanding in LLMs
Discourse particles are crucial elements that subtly shape the meaning of text.
Causal Interventions Reveal Shared Structure Across English Filler-Gap Constructions
Large Language Models (LLMs) have emerged as powerful sources of evidence for linguists seeking to develop theories of syntax.
A suite of LMs comprehend puzzle statements as well as humans
Using the same stimuli, we report a preregistered study comparing human responses in two conditions: one allowed rereading (replicating the original study), and one that restricted rereading (a more naturalistic comprehension test).
Both Direct and Indirect Evidence Contribute to Dative Alternation Preferences in Language Models
Language models (LMs) tend to show human-like preferences on a number of syntactic phenomena, but the extent to which these are attributable to direct exposure to the phenomena or more general properties of language is unclear.
Language Models Fail to Introspect About Their Knowledge of Language
Our findings complicate recent results suggesting that models can introspect, and add new evidence to the argument that prompted responses should not be conflated with models' linguistic generalizations.
Constructions are Revealed in Word Distributions
Construction grammar posits that constructions (form-meaning pairings) are acquired through experience with language (the distributional learning hypothesis).
Linguistic Generalizations are not Rules: Impacts on Evaluation of LMs
Linguistic evaluations of how well LMs generalize to produce or understand novel text often implicitly take for granted that natural languages are generated by symbolic rules.
How Linguistics Learned to Stop Worrying and Love the Language Models
On the other side, there have been claims that the success of LMs obviates the need for studying linguistic theory and structure.
Models Can and Should Embrace the Communicative Nature of Human-Generated Math
Math is constructed by people for people: just as natural language corpora reflect not just propositions but the communicative goals of language users, the math data that models are trained on reflects not just idealized mathematical entities but rich communicative intentions.
To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
Chain-of-thought (CoT) via prompting is the de facto method for eliciting reasoning capabilities from large language models (LLMs).
Do they mean 'us'? Interpreting Referring Expressions in Intergroup Bias
We curate a unique dataset of over 6 million game-time comments from opposing perspectives (the teams in the game), each comment grounded in a non-linguistic description of the events that precipitated these comments (live win probabilities for each team).
Participle-Prepended Nominals Have Lower Entropy Than Nominals Appended After the Participle
That is, we compare the entropy of $\alpha$ in compound construction slots like $\alpha$-[V]ed to the entropy of $\alpha$ in phrasal constructions like [V]ed by $\alpha$ for a given verb V. As predicted, there is significantly lower entropy in the compound construction than in the phrasal construction.
Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs
To that end, we iteratively trained transformer language models on systematically manipulated corpora which were human-scale in size, and then evaluated their learning of a rare grammatical phenomenon: the English Article+Adjective+Numeral+Noun (AANN) construction (``a beautiful five days'').
Language models align with human judgments on key grammatical constructions
Do large language models (LLMs) make human-like linguistic generalizations?
Mission: Impossible Language Models
Chomsky and others have very directly claimed that large language models (LLMs) are equally capable of learning languages that are possible and impossible for humans to learn.
Experimental Contexts Can Facilitate Robust Semantic Property Inference in Language Models, but Inconsistently
Recent zero-shot evaluations have highlighted important limitations in the abilities of language models (LMs) to perform meaning extraction.
Are Language Models More Like Libraries or Like Librarians? Bibliotechnism, the Novel Reference Problem, and the Attitudes of LLMs
A challenge for this idea, which we call bibliotechnism, is that LLMs generate novel text.
Revisiting the Optimality of Word Lengths
Under this method, we find that a language's word lengths should instead be proportional to the surprisal's expectation plus its variance-to-mean ratio.
Counterfactually Probing Language Identity in Multilingual Models
We use one such technique, AlterRep, a method of counterfactual probing, to explore the internal structure of multilingual models (mBERT and XLM-R).
Lil-Bevo: Explorations of Strategies for Training Language Models in More Humanlike Ways
We pretrained our masked language models with three ingredients: an initial pretraining with music data, training on shorter sequences before training on longer ones, and masking specific tokens to target some of the BLiMP subtasks.
Counterfactual Probing for the Influence of Affect and Specificity on Intergroup Bias
While existing work on studying bias in NLP focues on negative or pejorative language use, Govindarajan et al. (2023) offer a revised framing of bias in terms of intergroup social context, and its effects on language behavior.
Elaborative Simplification as Implicit Questions Under Discussion
Automated text simplification, a technique useful for making text more accessible to people such as children and emergent bilinguals, is often thought of as a monolingual translation task from complex sentences to simplified sentences using encoder-decoder models.
For Generated Text, Is NLI-Neutral Text the Best Text?
We explore incorporating natural language inference (NLI) into the text generative pipeline by using a pre-trained NLI model to assess whether a generated sentence entails, contradicts, or is neutral to the prompt and preceding text.
A Discerning Several Thousand Judgments: GPT-3 Rates the Article + Adjective + Numeral + Noun Construction
I validate the prompt using the CoLA corpus of acceptability judgments and then zero in on the AANN construction.
Dissociating language and thought in large language models
Large Language Models (LLMs) have come closest among all models to date to mastering human language, yet opinions about their linguistic and cognitive capabilities remain split.
Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training
Language tasks involving character-level manipulations (e. g., spelling corrections, arithmetic operations, word games) are challenging for models operating on subword units.
Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality
Recent visuolinguistic pre-trained models show promising progress on various end tasks such as image retrieval and video captioning.
longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks
Developing methods to adversarially challenge NLP systems is a promising avenue for improving both model performance and interpretability.
What do tokens know about their characters and how do they know it?
Pre-trained language models (PLMs) that use subword tokenization schemes can succeed at a variety of language tasks that require character-level information, despite lacking explicit access to the character composition of tokens.
When classifying grammatical role, BERT doesn't care about word order... except when it matters
Because meaning can often be inferred from lexical semantics alone, word order is often a redundant cue in natural language.
Grammatical cues to subjecthood are redundant in a majority of simple clauses across languages
The conclusion is that grammatical cues such as word order are necessary to convey subjecthood and objecthood in a minority of naturally occurring transitive clauses; nevertheless, they can (a) provide an important source of redundancy and (b) are crucial for conveying intended meaning that cannot be inferred from the words alone, including descriptions of human interactions, where roles are often reversible (e. g., Ray helped Lu/Lu helped Ray), and expressing non-prototypical meanings (e. g., "The bone chewed the dog.
A Massively Multilingual Analysis of Cross-linguality in Shared Embedding Space
We verify some of our linguistic findings by looking at the effect of morphological segmentation on English-Inuktitut alignment, in addition to examining the effect of word order agreement on isomorphism for 66 zero-shot language pairs from a different corpus.
How (Non-)Optimal is the Lexicon?
Examining corpora from 7 typologically diverse languages, we use those upper bounds to quantify the lexicon's optimality and to explore the relative costs of major constraints on natural codes.
Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP
Cryptic crosswords, the dominant crossword variety in the UK, are a promising target for advancing NLP systems that seek to process semantically complex, highly compositional language.
Deep Subjecthood: Higher-Order Grammatical Features in Multilingual BERT
Further examining the characteristics that our classifiers rely on, we find that features such as passive voice, animacy and case strongly correlate with classification decisions, suggesting that mBERT does not encode subjecthood purely syntactically, but that subjecthood embedding is continuous and dependent on semantic and discourse factors, as is proposed in much of the functional linguistics literature.
With Little Power Comes Great Responsibility
Despite its importance to experimental design, statistical power (the probability that, given a real effect, an experiment will reject the null hypothesis) has largely been ignored by the NLP community.
Response to Liu, Xu, and Liang (2015) and Ferrer-i-Cancho and Gómez-Rodríguez (2015) on Dependency Length Minimization
We address recent criticisms (Liu et al., 2015; Ferrer-i-Cancho and G\'omez-Rodr\'iguez, 2015) of our work on empirical evidence of dependency length minimization across languages (Futrell et al., 2015).
