Generalization

Frequency information on co-occurrence patterns can be automati- cally collected from a syntactically analyzed corpus; this information can then serve as the basis for selectional constraints when analyz- ing new …...

Machine translation benefits from system combination. We propose flexible interaction of hypergraphs as a novel technique combin- ing different translation models within one de- coder. We introduce features controlling the …...

AbstractThis paper presents the evaluation of the translation quality and Cross-Lingual Information Retrieval (CLIR) performance when using session information as the context of queries. The hypothesis is that previous queries …...

AbstractSystematic compositionality is the ability to recombine meaningful units with regular and predictable outcomes, and it’s seen as key to the human capacity for generalization in language. Recent work (Lake …...

One key challenge for building a semantic parser in new domains is the difficulty to an- notate new datasets. In this paper, we pro- pose a sequential transfer learning method …...

AbstractHuman translators often resort to different non-literal translation techniques besides the literal translation, such as idiom equivalence, generalization, particularization, semantic modulation, etc., especially when the source and target languages have …...

AbstractA sequence-to-sequence (seq2seq) learning with neural networks empirically shows to be an effective framework for grammatical error correction (GEC), which takes a sentence with errors as input and outputs the …...

AbstractNeural networks are surprisingly good at interpolating and perform remarkably well when the training set examples resemble those in the test set. However, they are often unable to extrapolate patterns …...

AbstractIn order to combat overfitting and in pursuit of better generalization, label smoothing is widely applied in modern neural machine translation systems. The core idea is to penalize over-confident outputs …...

AbstractCommonsense reasoning benchmarks have been largely solved by fine-tuning language models. The downside is that fine-tuning may cause models to overfit to task-specific data and thereby forget their knowledge gained …...

The adoption of natural language generation (NLG) models can leave individuals vulnera- ble to the generation of harmful information memorized by the models, such as conspiracy theories. While previous studies …...

AbstractWe address the problem of enhancing model robustness through regularization. Specifically, we focus on methods that regularize the model posterior difference between clean and noisy inputs. Theoretically, we provide a …...

AbstractFor task-oriented dialog systems to be maximally useful, it must be able to process conversations in a way that is (1) generalizable with a small number of training examples for …...

AbstractExisting Math Word Problem (MWP) solvers have achieved high accuracy on benchmark datasets. However, prior works have shown that such solvers do not generalize well and rely on superficial cues …...

AbstractDeep neural models have become the mainstream in answer selection, yielding state-of-the-art performance. However, these models tend to rely on spurious correlations between prediction labels and input features, which in …...

AbstractBased on the tremendous success of pre-trained language models (PrLMs) for source code comprehension tasks, current literature studies either ways to further improve the performance (generalization) of PrLMs, or their …...

Abstract“Zero-shot stance detection intends to detect previously unseen targets’ stances in the testingphase. However, achieving this goal can be difficult, as it requires minimizing the domain trans-fer between different targets, …...

AbstractDespite the tremendous success of Neural Machine Translation (NMT), its performance on low- resource language pairs still remains subpar, partly due to the limited ability to handle previously unseen inputs, …...

AbstractRecent work on the Retrieval-Enhanced Transformer (RETRO) model has shown impressive results: off-loading memory from trainable weights to a retrieval database can significantly improve language modeling and match the performance …...

AbstractRecent advances in discourse parsing performance create the impression that, as in other NLP tasks, performance for high-resource languages such as English is finally becoming reliable. In this paper we …...