Ideally, if a PRF model can distinguish between irrelevant and relevant information in the feedback, the more feedback documents there are, the better the revised query will be.
It is because the end-to-end supervised learning on task-specific dataset makes model overemphasize the data sample bias and task-specific signals instead of the essential matching signals, which ruins the generalization of model to different tasks.
Ensemble-based debiasing methods have been shown effective in mitigating the reliance of classifiers on specific dataset bias, by exploiting the output of a bias-only model to adjust the learning target.
The proposed transductive learning approach is general and effective to the task of unsupervised style transfer, and we will apply it to the other two typical methods in the future.
Information seeking is an essential step for open-domain question answering to efficiently gather evidence from a large corpus.
Ranked #2 on Question Answering on HotpotQA
We further extend these constraints to the semantic settings, which are shown to be better satisfied for all the deep text matching models.
Experimental results base on three publicly available benchmarks showed that in both of the implementations, Pre-Rank can respectively outperform the underlying ranking models and achieved state-of-the-art performances.
In the sketch stage, a skeleton is extracted by removing words which are conflict to the counterfactual condition, from the original ending.
However, these models designed for short texts cannot well address the long-form text matching problem, because there are many contexts in long-form texts can not be directly aligned with each other, and it is difficult for existing models to capture the key matching signals from such noisy data.
However, generating personalized responses is still a challenging task since the leverage of predefined persona information is often insufficient.
Aspect-based sentiment analysis (ABSA) aims to determine the sentiment polarity of each specific aspect in a given sentence.
Following this definition, a new dataset namely TRANCE is constructed on the basis of CLEVR, including three levels of settings, i. e.~Basic (single-step transformation), Event (multi-step transformation), and View (multi-step transformation with variant views).
Four popular text matching methods have been exploited in the paper.
This paper proposes a novel approach to learn commonsense from images, instead of limited raw texts or costly constructed knowledge bases, for the commonsense reasoning problem in NLP.
Therefore, an ideal dialogue generation models should be able to capture the topic information of each context, detect the relevant context, and produce appropriate responses accordingly.
To tackle this problem, we propose a Ranking Enhanced Dialogue generation framework in this paper.
Robust Reinforcement Learning aims to find the optimal policy with some extent of robustness to environmental dynamics.
To fill this gap, we switch to a ranking perspective that sorts the hypotheses in order of their plausibilities.
In learning-to-rank for information retrieval, a ranking model is automatically learned from the data and then utilized to rank the sets of retrieved documents.
Then, the self-attention mechanism is utilized to update both the context and masked response representation.
Ranking models lie at the heart of research on information retrieval (IR).
However, the performances of such models are not so good as that in the RC task.
We show in the experiments that Pommerman is a perfect environment for studying continual learning, and the agent can improve its performance by continually learning new skills without forgetting the old ones.
The main idea is to represent the weight matrix of the locally connected layer as the product of the kernel and the smoother, where the kernel is shared over different local receptive fields, and the smoother is for determining the importance and relations of different local receptive fields.
This paper concerns a deep learning approach to relevance ranking in information retrieval (IR).
Therefore, it is necessary to identify the difference between automatically learned features by deep IR models and hand-crafted features used in traditional learning to rank approaches.
In recent years, deep neural models have been widely adopted for text matching tasks, such as question answering and information retrieval, showing improved performance as compared with previous methods.
Although ad-hoc retrieval can also be formalized as a text matching task, few deep models have been tested on it.
In this paper, we propose to view the generation of the global interaction between two texts as a recursive process: i. e. the interaction of two texts at each position is a composition of the interactions between their prefixes as well as the word level interaction at the current position.
An effective way is to extract meaningful matching patterns from words, phrases, and sentences to produce the matching score.
Our model has several advantages: (1) By using Bi-LSTM, rich context of the whole sentence is leveraged to capture the contextualized local information in each positional sentence representation; (2) By matching with multiple positional sentence representations, it is flexible to aggregate different important contextualized local information in a sentence to support the matching; (3) Experiments on different tasks such as question answering and sentence completion demonstrate the superiority of our model.
The ICDM Challenge 2013 is to apply machine learning to the problem of hotel ranking, aiming to maximize purchases according to given hotel characteristics, location attractiveness of hotels, user's aggregated purchase history and competitive online travel agency information for each potential hotel choice.