This paper presents CLEAR, a retrieval model that seeks to complement classical lexical exact-match models such as BM25 with semantic matching signals from a neural embedding matching model. CLEAR explicitly trains the neural embedding to encode lang
uage structures and semantics that lexical retrieval fails to capture with a novel residual-based embedding learning method. Empirical evaluations demonstrate the advantages of CLEAR over state-of-the-art retrieval models, and that it can substantially improve the end-to-end accuracy and efficiency of reranking pipelines.
We propose a novel method for hierarchical entity classification that embraces ontological structure at both training and during prediction. At training, our novel multi-level learning-to-rank loss compares positive types against negative siblings ac
cording to the type tree. During prediction, we define a coarse-to-fine decoder that restricts viable candidates at each level of the ontology based on already predicted parent type(s). We achieve state-of-the-art across multiple datasets, particularly with respect to strict accuracy.
We ask whether text understanding has progressed to where we may extract event information through incremental refinement of bleached statements derived from annotation manuals. Such a capability would allow for the trivial construction and extension
of an extraction framework by intended end-users through declarations such as, Some person was born in some location at some time. We introduce an example of a model that employs such statements, with experiments illustrating we can extract events under closed ontologies and generalize to unseen event types simply by reading new definitions.
We present Espresso, an open-source, modular, extensible end-to-end neural automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch and the popular neural machine translation toolkit fairseq. Espresso supports distributed
training across GPUs and computing nodes, and features various decoding approaches commonly employed in ASR, including look-ahead word-based language model fusion, for which a fast, parallelized decoder is implemented. Espresso achieves state-of-the-art ASR performance on the WSJ, LibriSpeech, and Switchboard data sets among other end-to-end systems without data augmentation, and is 4--11x faster for decoding than similar systems (e.g. ESPnet).
We introduce Uncertain Natural Language Inference (UNLI), a refinement of Natural Language Inference (NLI) that shifts away from categorical labels, targeting instead the direct prediction of subjective probability assessments. We demonstrate the fea
sibility of collecting annotations for UNLI by relabeling a portion of the SNLI dataset under a probabilistic scale, where items even with the same categorical label differ in how likely people judge them to be true given a premise. We describe a direct scalar regression modeling approach, and find that existing categorically labeled NLI data can be used in pre-training. Our best models approach human performance, demonstrating models may be capable of more subtle inferences than the categorical bin assignment employed in current NLI tasks.
Researchers illustrate improvements in contextual encoding strategies via resultant performance on a battery of shared Natural Language Understanding (NLU) tasks. Many of these tasks are of a categorical prediction variety: given a conditioning conte
xt (e.g., an NLI premise), provide a label based on an associated prompt (e.g., an NLI hypothesis). The categorical nature of these tasks has led to common use of a cross entropy log-loss objective during training. We suggest this loss is intuitively wrong when applied to plausibility tasks, where the prompt by design is neither categorically entailed nor contradictory given the context. Log-loss naturally drives models to assign scores near 0.0 or 1.0, in contrast to our proposed use of a margin-based loss. Following a discussion of our intuition, we describe a confirmation study based on an extreme, synthetically curated task derived from MultiNLI. We find that a margin-based loss leads to a more plausible model of plausibility. Finally, we illustrate improvements on the Choice Of Plausible Alternative (COPA) task through this change in loss.
Tracking the state of the conversation is a central component in task-oriented spoken dialogue systems. One such approach for tracking the dialogue state is slot carryover, where a model makes a binary decision if a slot from the context is relevant
to the current turn. Previous work on the slot carryover task used models that made independent decisions for each slot. A close analysis of the results show that this approach results in poor performance over longer context dialogues. In this paper, we propose to jointly model the slots. We propose two neural network architectures, one based on pointer networks that incorporate slot ordering information, and the other based on transformer networks that uses self attention mechanism to model the slot interdependencies. Our experiments on an internal dialogue benchmark dataset and on the public DSTC2 dataset demonstrate that our proposed models are able to resolve longer distance slot references and are able to achieve competitive performance.
A precondition for a No Free Lunch theorem is evaluation with a loss function which does not assume a priori superiority of some outputs over others. A previous result for community detection by Peel et al. (2017) relies on a mismatch between the los
s function and the problem domain. The loss function computes an expectation over only a subset of the universe of possible outputs; thus, it is only asymptotically appropriate with respect to the problem size. By using the correct random model for the problem domain, we provide a stronger, exact No Free Lunch theorem for community detection. The claim generalizes to other set-partitioning tasks including core/periphery separation, $k$-clustering, and graph partitioning. Finally, we review the literature of proposed evaluation functions and identify functions which (perhaps with slight modifications) are compatible with an exact No Free Lunch theorem.
We present a novel approach to dialogue state tracking and referring expression resolution tasks. Successful contextual understanding of multi-turn spoken dialogues requires resolving referring expressions across turns and tracking the entities relev
ant to the conversation across turns. Tracking conversational state is particularly challenging in a multi-domain scenario when there exist multiple spoken language understanding (SLU) sub-systems, and each SLU sub-system operates on its domain-specific meaning representation. While previous approaches have addressed the disparate schema issue by learning candidate transformations of the meaning representation, in this paper, we instead model the reference resolution as a dialogue context-aware user query reformulation task -- the dialog state is serialized to a sequence of natural language tokens representing the conversation. We develop our model for query reformulation using a pointer-generator network and a novel multi-task learning setup. In our experiments, we show a significant improvement in absolute F1 on an internal as well as a, soon to be released, public benchmark respectively.
The problem of community detection receives great attention in recent years. Many methods have been proposed to discover communities in networks. In this paper, we propose a Gaussian stochastic blockmodel that uses Gaussian distributions to fit weigh
t of edges in networks for non-overlapping community detection. The maximum likelihood estimation of this model has the same objective function as general label propagation with node preference. The node preference of a specific vertex turns out to be a value proportional to the intra-community eigenvector centrality (the corresponding entry in principal eigenvector of the adjacency matrix of the subgraph inside that vertexs community) under maximum likelihood estimation. Additionally, the maximum likelihood estimation of a constrained version of our model is highly related to another extension of label propagation algorithm, namely, the label propagation algorithm under constraint. Experiments show that the proposed Gaussian stochastic blockmodel performs well on various benchmark networks.
