Search Results for author:
Found 88 papers, 28 papers with code
Online Semantic Parsing for Latency Reduction in Task-Oriented Dialogue
Standard conversational semantic parsing maps a complete user utterance into an executable program, after which the program is executed to respond to the user.
LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error
We find that existing LLMs, including GPT-4 and open-source LLMs specifically fine-tuned for tool use, only reach a correctness rate in the range of 30% to 60%, far from reliable use in practice.
Principled Gradient-based Markov Chain Monte Carlo for Text Generation
Recent papers have demonstrated the possibility of energy-based text generation by adapting gradient-based sampling algorithms, a paradigm of MCMC algorithms that promises fast convergence.
Do Androids Know They're Only Dreaming of Electric Sheep?
We design probes trained on the internal representations of a transformer language model that are predictive of its hallucinatory behavior on in-context generation tasks.
Structure-Aware Path Inference for Neural Finite State Transducers
In this paper, we focus on the resulting challenge of imputing the latent alignment path that explains a given pair of input and output strings (e. g., during training).
A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia
Yet the mechanisms underlying this contextual grounding remain unknown, especially in situations where contextual information contradicts factual knowledge stored in the parameters, which LLMs also excel at recalling.
Interpreting User Requests in the Context of Natural Language Standing Instructions
Users of natural language interfaces, generally powered by Large Language Models (LLMs), often must repeat their preferences each time they make a similar request.
SCREWS: A Modular Framework for Reasoning with Revisions
To enable exploration in this space, we present SCREWS, a modular framework for reasoning with revisions.
Efficient Semiring-Weighted Earley Parsing
This paper provides a reference description, in the form of a deduction system, of Earley's (1970) context-free parsing algorithm with various speed-ups.
Decision-Oriented Dialogue for Human-AI Collaboration
In each of these settings, AI assistants and users have disparate abilities that they must combine to arrive at the best decision: assistants can access and process large amounts of information, while users have preferences and constraints external to the system.
Autoregressive Modeling with Lookahead Attention
To predict the next token, autoregressive models ordinarily examine the past.
Algorithms for Acyclic Weighted Finite-State Automata with Failure Arcs
The pathsum in ordinary acyclic WFSAs is efficiently computed by the backward algorithm in time $O(|E|)$, where $E$ is the set of transitions.
A Measure-Theoretic Characterization of Tight Language Models
Language modeling, a central task in natural language processing, involves estimating a probability distribution over strings.
Privacy-Preserving Domain Adaptation of Semantic Parsers
Task-oriented dialogue systems often assist users with personal or confidential matters.
Contrastive Decoding: Open-ended Text Generation as Optimization
We propose contrastive decoding (CD), a reliable decoding approach that optimizes a contrastive objective subject to a plausibility constraint.
The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding
Satisfying these constraints simultaneously is difficult for the two predominant paradigms in language generation: neural language modeling and rule-based generation.
On the Intersection of Context-Free and Regular Languages
It shows, by a simple construction, that the intersection of a context-free language and a regular language is itself context-free.
BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing
We introduce BenchCLAMP, a Benchmark to evaluate Constrained LAnguage Model Parsing, that includes context-free grammars for seven semantic parsing datasets and two syntactic parsing datasets with varied output representations, as well as a constrained decoding interface to generate only valid outputs covered by these grammars.
Non-Programmers Can Label Programs Indirectly via Active Examples: A Case Study with Text-to-SQL
We introduce APEL, a framework in which non-programmers select among candidate programs generated by a seed semantic parser (e. g., Codex).
When More Data Hurts: A Troubling Quirk in Developing Broad-Coverage Natural Language Understanding Systems
Rejecting class imbalance as the sole culprit, we reveal that the trend is closely associated with an effect we call source signal dilution, where strong lexical cues for the new symbol become diluted as the training dataset grows.
Transformer Embeddings of Irregularly Spaced Events and Their Participants
The neural Hawkes process (Mei & Eisner, 2017) is a generative model of irregularly spaced sequences of discrete events.
Searching for More Efficient Dynamic Programs
To this end, we describe a set of program transformations, a simple metric for assessing the efficiency of a transformed program, and a heuristic search procedure to improve this metric.
Constrained Language Models Yield Few-Shot Semantic Parsers
We explore the use of large pretrained language models as few-shot semantic parsers.
Learning How to Ask: Querying LMs with Mixtures of Soft Prompts
We explore the idea of learning prompts by gradient descent -- either fine-tuning prompts taken from previous work, or starting from random initialization.
Noise-Contrastive Estimation for Multivariate Point Processes
The log-likelihood of a generative model often involves both positive and negative terms.
Limitations of Autoregressive Models and Their Alternatives
Standard autoregressive language models perform only polynomial-time computation to compute the probability of the next symbol.
Evaluation of Logic Programs with Built-Ins and Aggregation: A Calculus for Bag Relations
We present a scheme for translating logic programs, which may use aggregation and arithmetic, into algebraic expressions that denote bag relations over ground terms of the Herbrand universe.
Programming Languages Symbolic Computation
Task-Oriented Dialogue as Dataflow Synthesis
We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph.
Neural Datalog Through Time: Informed Temporal Modeling via Logical Specification
Learning how to predict future events from patterns of past events is difficult when the set of possible event types is large.
A Corpus for Large-Scale Phonetic Typology
A major hurdle in data-driven research on typology is having sufficient data in many languages to draw meaningful conclusions.
Spelling-Aware Construction of Macaronic Texts for Teaching Foreign-Language Vocabulary
We present a machine foreign-language teacher that modifies text in a student{'}s native language (L1) by replacing some word tokens with glosses in a foreign language (L2), in such a way that the student can acquire L2 vocabulary simply by reading the resulting macaronic text.
Specializing Word Embeddings (for Parsing) by Information Bottleneck
Pre-trained word embeddings like ELMo and BERT contain rich syntactic and semantic information, resulting in state-of-the-art performance on various tasks.
Informed Temporal Modeling via Logical Specification of Factorial LSTMs
Consider a world in which events occur that involve various entities.
Simple Construction of Mixed-Language Texts for Vocabulary Learning
We accomplish this by modifying a cloze language model to incrementally learn new vocabulary items, and use this language model as a proxy for the word guessing and learning ability of real students.
A Generative Model for Punctuation in Dependency Trees
When the tree's yield is rendered as a written sentence, a string rewriting mechanism transduces the underlying marks into "surface" marks, which are part of the observed (surface) string but should not be regarded as part of the tree.
What Kind of Language Is Hard to Language-Model?
Trying to answer the question of what features difficult languages have in common, we try and fail to reproduce our earlier (Cotterell et al., 2018) observation about morphological complexity and instead reveal far simpler statistics of the data that seem to drive complexity in a much larger sample.
Neural Finite-State Transducers: Beyond Rational Relations
We introduce neural finite state transducers (NFSTs), a family of string transduction models defining joint and conditional probability distributions over pairs of strings.
Imputing Missing Events in Continuous-Time Event Streams
On held-out incomplete sequences, our method is effective at inferring the ground-truth unobserved events, with particle smoothing consistently improving upon particle filtering.
Contextualization of Morphological Inflection
Critical to natural language generation is the production of correctly inflected text.
UniMorph 2.0: Universal Morphology
The Universal Morphology UniMorph project is a collaborative effort to improve how NLP handles complex morphology across the world's languages.
The CoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection
Apart from extending the number of languages involved in earlier supervised tasks of generating inflected forms, this year the shared task also featured a new second task which asked participants to inflect words in sentential context, similar to a cloze task.
Synthetic Data Made to Order: The Case of Parsing
To approximately parse an unfamiliar language, it helps to have a treebank of a similar language.
Inference of unobserved event streams with neural Hawkes particle smoothing
Particle smoothing is an extension of particle filtering in which proposed events are conditioned on the future as well as the past.
On the Complexity and Typology of Inflectional Morphological Systems
We quantify the linguistic complexity of different languages' morphological systems.
A Deep Generative Model of Vowel Formant Typology
What makes some types of languages more probable than others?
Are All Languages Equally Hard to Language-Model?
For general modeling methods applied to diverse languages, a natural question is: how well should we expect our models to work on languages with differing typological profiles?
Unsupervised Disambiguation of Syncretism in Inflected Lexicons
Lexical ambiguity makes it difficult to compute various useful statistics of a corpus.
Neural Particle Smoothing for Sampling from Conditional Sequence Models
We introduce neural particle smoothing, a sequential Monte Carlo method for sampling annotations of an input string from a given probability model.
On the Diachronic Stability of Irregularity in Inflectional Morphology
Many languages' inflectional morphological systems are replete with irregulars, i. e., words that do not seem to follow standard inflectional rules.
Spell Once, Summon Anywhere: A Two-Level Open-Vocabulary Language Model
By invoking the second RNN to generate spellings for novel words in context, we obtain an open-vocabulary language model.
Surface Statistics of an Unknown Language Indicate How to Parse It
We show experimentally across multiple languages: (1) Features computed from the unparsed corpus improve parsing accuracy.
Fine-Grained Prediction of Syntactic Typology: Discovering Latent Structure with Supervised Learning
We show how to predict the basic word-order facts of a novel language given only a corpus of part-of-speech (POS) sequences.
The Galactic Dependencies Treebanks: Getting More Data by Synthesizing New Languages
We release Galactic Dependencies 1. 0---a large set of synthetic languages not found on Earth, but annotated in Universal Dependencies format.
Knowledge Tracing in Sequential Learning of Inflected Vocabulary
We present a feature-rich knowledge tracing method that captures a student{'}s acquisition and retention of knowledge during a foreign language phrase learning task.
Bayesian Modeling of Lexical Resources for Low-Resource Settings
Practically, this means that we may treat the lexical resources as observations under the proposed generative model.
Low Resource Named Entity Recognition
named-entity-recognition
+2
CoNLL-SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection in 52 Languages
In sub-task 2, systems were given a lemma and some of its specific inflected forms, and asked to complete the inflectional paradigm by predicting all of the remaining inflected forms.
Probabilistic Typology: Deep Generative Models of Vowel Inventories
Linguistic typology studies the range of structures present in human language.
Explaining and Generalizing Skip-Gram through Exponential Family Principal Component Analysis
The popular skip-gram model induces word embeddings by exploiting the signal from word-context coocurrence.
Learning to Prune: Exploring the Frontier of Fast and Accurate Parsing
Pruning hypotheses during dynamic programming is commonly used to speed up inference in settings such as parsing.
The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process
Many events occur in the world.
Approximation-Aware Dependency Parsing by Belief Propagation
We show how to adjust the model parameters to compensate for the errors introduced by this approximation, by following the gradient of the actual loss on training data.
Modeling Word Forms Using Latent Underlying Morphs and Phonology
Given some surface word types of a concatenative language along with the abstract morpheme sequences that they express, we show how to recover consistent underlying forms for these morphemes, together with the (stochastic) phonology that maps each concatenation of underlying forms to a surface form.
Learned Prioritization for Trading Off Accuracy and Speed
Users want natural language processing (NLP) systems to be both fast and accurate, but quality often comes at the cost of speed.
Imitation Learning by Coaching
However, it is important to note that these guarantees depend on how well the policy we found can imitate the oracle on the training data.
