This is a list of all the questions and their associated study carrel identifiers. One can learn a lot of the "aboutness" of a text simply by reading the questions.
| identifier | question |
|---|---|
| cord-020912-tbq7okmj | a large- scale hierarchical image database VSE++: improving visual- semantic embeddings with hard negatives Cross- modal retrieval with correspondence autoencoder Topic models for image annotation and text illustration Easy as ABC?: facilitating pictorial communication via semantically enhanced layout Canonical correlation analysis: an overview with application to learning methods Cross- modal retrieval via deep and bidirectional representation learning Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies |
| cord-020834-ch0fg9rp | How did these innovations make their way from the"ivory tower"into the"real world"? |
| cord-020834-ch0fg9rp | One obvious question is: Why did it take so long? |
| cord-020811-pacy48qx | RQ2: Can we automatically update an existing sentiment lexicon given a new corpus from the same domain( i.e., to extend an existing lexicon to have more entries) or from a different domain( i.e., to adapt the existing lexicon to a new domain-domain adaptation)? |
| cord-020811-pacy48qx | RQ3: How can we enrich the existing sentiment lexicons using information obtained from neural models( word embedding)? |
| cord-020811-pacy48qx | Specifically, we aim to answer the following three research questions: Can we automatically generate a sentiment lexicon from a corpus and improves the existing approaches? |
| cord-020888-ov2lzus4 | What does it mean to impose close representations for all images representing"Paris"( e.g."the Eiffel Tower","Louvre Museum"), even if they can be associated to the same textual unit? |
| cord-020888-ov2lzus4 | large vocabulary image annotation Learning semantic structure- preserved embeddings for cross- modal retrieval End- to- end neural ad- hoc ranking with kernel pooling How powerful are graph neural networks? |
| cord-020905-gw8i6tkn | What makes a helpful online review? |
| cord-020896-yrocw53j | ArXiv Multimodal vehicle detection: fusing 3D- lidar and color camera data Enriching word vectors with subword information Application of image analytics for disaster response in smart cities SMOTE: synthetic minority over- sampling technique ImageNet: a large- scale hierarchical image database How much data do we create every day? |
| cord-020896-yrocw53j | How transferable are features in deep neural networks? |
| cord-020815-j9eboa94 | Does this ambiguity “ matter ”? |
| cord-020815-j9eboa94 | Returning to our original motivating question regarding the multitude of BM25 variants:"Does it matter?", we conclude that the answer appears to be"no |
| cord-020815-j9eboa94 | You Mean? |
| cord-020903-qt0ly5d0 | What Can Task Teach Us About Query Reformulations? |
| cord-020830-97xmu329 | For example in( Since many days Mubarak did n't die.. is he sick or what? |
| cord-020909-n36p5n2k | De- biasing user preference ratings in recommender systems Hat- trie: a cache- conscious trie- based data structure for strings Man is to computer programmer as woman is to homemaker? |
| cord-020909-n36p5n2k | The Tyranny of data? |
| cord-020909-n36p5n2k | debiasing word embeddings Bias in algorithmic filtering and personalization Fair and balanced? |
| cord-020909-n36p5n2k | the bright and dark sides of data- driven decision- making for social good Is twitter a public sphere for online conflicts? |
| cord-020931-fymgnv1g | The concept of readability All mixed up? |
| cord-020936-k1upc1xu | For that purpose, we address the following question: for any friends- of- friends algorithm, such as Adamic- Adar[ 1] or the IR models, is it beneficial to reward the number of common users between the target and the candidate users? |
| cord-020936-k1upc1xu | However, once the weight is important for a model( and, therefore, EWC1 is important) does satisfying the rest of the edge weight constraints provide more accurate recommendations? |
| cord-020936-k1upc1xu | Information filtering and information retrieval: two sides of the same coin? |
| cord-020918-056bvngu | In this paper, we investigated whether the standard insights extraction pipeline is sufficient when applied to a single language family indigenous to Africa, Bantu languages, using the following questions:( 1) how well does the standard insights extraction pipeline apply to Bantu languages; and( 2) if found to be inadequate, why, and how can the pipeline be modified so as to be applicable to Bantu languages? |
| cord-020832-iavwkdpr | Annotated chemical patent corpus: a gold standard for text mining Automatic identification of relevant chemical compounds from patents Patents: a unique source for scientific technical information in chemistry related industry? |
| cord-020832-iavwkdpr | What are Usage Scenarios? |
| cord-020832-iavwkdpr | What are the Goals of This Evaluation Lab? |
| cord-020832-iavwkdpr | Why is This Lab Needed? |
| cord-020908-oe77eupc | Q1 Does data table content help in dataset retrieval? |
| cord-020908-oe77eupc | Q2 Do generated schema labels help in dataset retrieval? |
| cord-020908-oe77eupc | Q3 Which fields are most important for the dataset retrieval task? |
| cord-020901-aew8xr6n | In: CIKM Translating embeddings for modeling multi- relational data Empirical analysis of predictive algorithms for collaborative filtering TransNets: learning to transform for recommendation Are we really making much progress? |
| cord-020901-aew8xr6n | User models: theory, method, and practice TopicMF: simultaneously exploiting ratings and reviews for recommendation Classifying sentiment in microblogs: is brevity an advantage? |
| cord-020875-vd4rtxmz | Are deep learning approaches more effective compared to the state- of- the- art and traditional machine learning- based LMP approaches?, RQ2. |
| cord-020875-vd4rtxmz | How can the LMP systems control the trade- off between effectiveness and efficiency during crisis scenarios?. |
| cord-020875-vd4rtxmz | How can we reduce the effect of the scarcity of labeled data on the performance of the LMP system?, and RQ4. |
| cord-020875-vd4rtxmz | Would context expansion( using user's tweets, on- topic tweets, etc) improve LMP?, RQ3. |
| cord-020904-x3o3a45b | : How does our model perform with different retrieval functions to weight query terms? |
| cord-020904-x3o3a45b | How does our model perform compared to existing retrieval models? |
| cord-020904-x3o3a45b | RQ3: What is the effect of different principle functions for combining relevance evidence, including Aggregate Relevance( AR) principle and Disjunctive Relevance Decision( DRD), in our model? |
| cord-020891-lt3m8h41 | : an example Is question answering fit for the semantic web?: |
| cord-020891-lt3m8h41 | That is, a user might ask a rather"fuzzy"first question( such as"what are important topics in the field of'Information Retrieval'? |
| cord-020891-lt3m8h41 | The last information need( q 5) was formulated in a complex way("which authors that have written a book about criminal law have also written a review?") and required participants to recognise that a partial result to the question was already available from a previous step. |
| cord-020891-lt3m8h41 | This query, however, will not retrieve anything since the question contains an ellipsis: it should actually be formulated as"Which journals have published a review about it?". |
| cord-020914-7p37m92a | We should abandon fossil fuels( negative stance), c 3="Fossil fuels"( neutral stance), and c 4="Should fossil fuels be used?" |
| cord-020914-7p37m92a | Are you convinced? |
| cord-020914-7p37m92a | Choosing the more convincing evidence with a Siamese network What makes a convincing argument? |
| cord-020914-7p37m92a | Empirical analysis and detecting attributes of convincingness in web argumentation Which argument is more convincing? |